diff --git a/.pylintrc b/.pylintrc new file mode 100644 index 0000000..bf53a6c --- /dev/null +++ b/.pylintrc @@ -0,0 +1,377 @@ +[MASTER] +# Use multiple processes to speed up Pylint. +jobs=1 + +init-hook='import sys; sys.path.append("knead/")' + +# Allow loading of arbitrary C extensions. Extensions are imported into the +# active Python interpreter and may run arbitrary code. +unsafe-load-any-extension=no + +# Allow optimization of some AST trees. This will activate a peephole AST +# optimizer, which will apply various small optimizations. For instance, it can +# be used to obtain the result of joining multiple strings with the addition +# operator. Joining a lot of strings can lead to a maximum recursion error in +# Pylint and this flag can prevent that. It has one side effect, the resulting +# AST will be different than the one from reality. +optimize-ast=no + +[MESSAGES CONTROL] + +# Only show warnings with the listed confidence levels. Leave empty to show +# all. Valid levels: HIGH, INFERENCE, INFERENCE_FAILURE, UNDEFINED +confidence= + +# Disable the message, report, category or checker with the given id(s). You +# can either give multiple identifiers separated by comma (,) or put this +# option multiple times (only on the command line, not in the configuration +# file where it should appear only once).You can also use "--disable=all" to +# disable everything first and then reenable specific checks. For example, if +# you want to run only the similarities checker, you can use "--disable=all +# --enable=similarities". If you want to run only the classes checker, but have +# no Warning level messages displayed, use"--disable=all --enable=classes +# --disable=W" +# +# Disable warnings, missing-docstring errors and wrong indentation errors +disable=W,C0111,C0330 + +# Enable the message, report, category or checker with the given id(s). You can +# either give multiple identifier separated by comma (,) or put this option +# multiple time. See also the "--disable" option for examples. +enable=import-error, + import-self, + reimported, + wildcard-import, + misplaced-future, + relative-import, + deprecated-module, + unpacking-non-sequence, + invalid-all-object, + undefined-all-variable, + used-before-assignment, + cell-var-from-loop, + global-variable-undefined, + dangerous-default-value, + redefined-builtin, + redefine-in-handler, + unused-import, + unused-wildcard-import, + global-variable-not-assigned, + undefined-loop-variable, + global-statement, + global-at-module-level, + bad-open-mode, + redundant-unittest-assert, + boolean-datetime, + unused-variable + + +[REPORTS] + +# Set the output format. Available formats are text, parseable, colorized, msvs +# (visual studio) and html. You can also give a reporter class, eg +# mypackage.mymodule.MyReporterClass. +output-format=colorized + +# Put messages in a separate file for each module / package specified on the +# command line instead of printing them on stdout. Reports (if any) will be +# written in a file name "pylint_global.[txt|html]". +files-output=no + +# Tells whether to display a full report or only the messages +reports=no + +# Python expression which should return a note less than 10 (10 is the highest +# note). You have access to the variables errors warning, statement which +# respectively contain the number of errors / warnings messages and the total +# number of statements analyzed. This is used by the global evaluation report +# (RP0004). +evaluation=10.0 - ((float(5 * error + warning + refactor + convention) / statement) * 10) + +[BASIC] + +# List of builtins function names that should not be used, separated by a comma +bad-functions=map,filter,input + +# Good variable names which should always be accepted, separated by a comma +good-names=a,b,c,f,i,j,k,x,y,_,fig,ax + +# Bad variable names which should always be refused, separated by a comma +bad-names=foo,bar,baz,toto,tutu,tata + +# Colon-delimited sets of names that determine each other's naming style when +# the name regexes allow several styles. +name-group= + +# Include a hint for the correct naming format with invalid-name +include-naming-hint=yes + +# Regular expression matching correct method names +method-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Naming hint for method names +method-name-hint=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression matching correct function names +function-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Naming hint for function names +function-name-hint=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression matching correct module names +module-rgx=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$ + +# Naming hint for module names +module-name-hint=(([a-z_][a-z0-9_]*)|([A-Z][a-zA-Z0-9]+))$ + +# Regular expression matching correct attribute names +attr-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Naming hint for attribute names +attr-name-hint=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression matching correct class attribute names +class-attribute-rgx=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$ + +# Naming hint for class attribute names +class-attribute-name-hint=([A-Za-z_][A-Za-z0-9_]{2,30}|(__.*__))$ + +# Regular expression matching correct constant names +const-rgx=(([A-Z_][A-Z0-9_]*)|(__.*__))$ + +# Naming hint for constant names +const-name-hint=(([A-Z_][A-Z0-9_]*)|(__.*__))$ + +# Regular expression matching correct class names +class-rgx=[A-Z_][a-zA-Z0-9]+$ + +# Naming hint for class names +class-name-hint=[A-Z_][a-zA-Z0-9]+$ + +# Regular expression matching correct argument names +argument-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Naming hint for argument names +argument-name-hint=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression matching correct inline iteration names +inlinevar-rgx=[A-Za-z_][A-Za-z0-9_]*$ + +# Naming hint for inline iteration names +inlinevar-name-hint=[A-Za-z_][A-Za-z0-9_]*$ + +# Regular expression matching correct variable names +variable-rgx=[a-z_][a-z0-9_]{2,30}$ + +# Naming hint for variable names +variable-name-hint=[a-z_][a-z0-9_]{2,30}$ + +# Regular expression which should only match function or class names that do +# not require a docstring. +no-docstring-rgx=^_ + +# Minimum line length for functions/classes that require docstrings, shorter +# ones are exempt. +docstring-min-length=-1 + + +[ELIF] + +# Maximum number of nested blocks for function / method body +max-nested-blocks=5 + + +[FORMAT] + +# Maximum number of characters on a single line. +max-line-length=100 + +# Regexp for a line that is allowed to be longer than the limit. +ignore-long-lines=^\s*(# )??$ + +# Allow the body of an if to be on the same line as the test if there is no +# else. +single-line-if-stmt=no + +# List of optional constructs for which whitespace checking is disabled. `dict- +# separator` is used to allow tabulation in dicts, etc.: {1 : 1,\n222: 2}. +# `trailing-comma` allows a space between comma and closing bracket: (a, ). +# `empty-line` allows space-only lines. +no-space-check=trailing-comma,dict-separator + +# Maximum number of lines in a module +max-module-lines=1000 + +# String used as indentation unit. This is usually " " (4 spaces) or "\t" (1 +# tab). +indent-string=' ' + +# Number of spaces of indent required inside a hanging or continued line. +indent-after-paren=4 + +# Expected format of line ending, e.g. empty (any line ending), LF or CRLF. +expected-line-ending-format= + + +[LOGGING] + +# Logging modules to check that the string format arguments are in logging +# function parameter format +logging-modules=logging + + +[MISCELLANEOUS] + +# List of note tags to take in consideration, separated by a comma. +notes=FIXME,XXX,TODO + + +[SIMILARITIES] + +# Minimum lines number of a similarity. +min-similarity-lines=4 + +# Ignore comments when computing similarities. +ignore-comments=yes + +# Ignore docstrings when computing similarities. +ignore-docstrings=yes + +# Ignore imports when computing similarities. +ignore-imports=no + + +[SPELLING] + +# Spelling dictionary name. Available dictionaries: none. To make it working +# install python-enchant package. +spelling-dict= + +# List of comma separated words that should not be checked. +spelling-ignore-words= + +# A path to a file that contains private dictionary; one word per line. +spelling-private-dict-file= + +# Tells whether to store unknown words to indicated private dictionary in +# --spelling-private-dict-file option instead of raising a message. +spelling-store-unknown-words=no + + +[TYPECHECK] + +# Tells whether missing members accessed in mixin class should be ignored. A +# mixin class is detected if its name ends with "mixin" (case insensitive). +ignore-mixin-members=yes + +# List of module names for which member attributes should not be checked +# (useful for modules/projects where namespaces are manipulated during runtime +# and thus existing member attributes cannot be deduced by static analysis. It +# supports qualified module names, as well as Unix pattern matching. +ignored-modules= + +# List of classes names for which member attributes should not be checked +# (useful for classes with attributes dynamically set). This supports can work +# with qualified names. +ignored-classes= + +# List of members which are set dynamically and missed by pylint inference +# system, and so shouldn't trigger E1101 when accessed. Python regular +# expressions are accepted. +generated-members= + + +[VARIABLES] + +# Tells whether we should check for unused import in __init__ files. +init-import=no + +# A regular expression matching the name of dummy variables (i.e. expectedly +# not used). +dummy-variables-rgx=_$|dummy + +# List of additional names supposed to be defined in builtins. Remember that +# you should avoid to define new builtins when possible. +additional-builtins= + +# List of strings which can identify a callback function by name. A callback +# name must start or end with one of those strings. +callbacks=cb_,_cb + + +[CLASSES] + +# List of method names used to declare (i.e. assign) instance attributes. +defining-attr-methods=__init__,__new__,setUp + +# List of valid names for the first argument in a class method. +valid-classmethod-first-arg=cls + +# List of valid names for the first argument in a metaclass class method. +valid-metaclass-classmethod-first-arg=mcs + +# List of member names, which should be excluded from the protected access +# warning. +exclude-protected=_asdict,_fields,_replace,_source,_make + + +[DESIGN] + +# Maximum number of arguments for function / method +max-args=5 + +# Argument names that match this expression will be ignored. Default to name +# with leading underscore +ignored-argument-names=_.* + +# Maximum number of locals for function / method body +max-locals=15 + +# Maximum number of return / yield for function / method body +max-returns=6 + +# Maximum number of branch for function / method body +max-branches=12 + +# Maximum number of statements in function / method body +max-statements=50 + +# Maximum number of parents for a class (see R0901). +max-parents=7 + +# Maximum number of attributes for a class (see R0902). +max-attributes=7 + +# Minimum number of public methods for a class (see R0903). +min-public-methods=2 + +# Maximum number of public methods for a class (see R0904). +max-public-methods=20 + +# Maximum number of boolean expressions in a if statement +max-bool-expr=5 + + +[IMPORTS] + +# Deprecated modules which should not be used, separated by a comma +deprecated-modules=optparse + +# Create a graph of every (i.e. internal and external) dependencies in the +# given file (report RP0402 must not be disabled) +import-graph= + +# Create a graph of external dependencies in the given file (report RP0402 must +# not be disabled) +ext-import-graph= + +# Create a graph of internal dependencies in the given file (report RP0402 must +# not be disabled) +int-import-graph= + + +[EXCEPTIONS] + +# Exceptions that will emit a warning when being caught. Defaults to +# "Exception" +overgeneral-exceptions=Exception diff --git a/Makefile b/Makefile index 5905a62..0e5b0e1 100644 --- a/Makefile +++ b/Makefile @@ -1,4 +1,4 @@ -.PHONY: help venv test publish clean +.PHONY: help venv lint-black lint-pylint lint test check black publish clean .DEFAULT_GOAL = help PYTHON = python3 @@ -21,8 +21,27 @@ venv: # Set up Python virtual environment. ) @printf "\n\nVirtual environment created! \033[1;34mRun \`source ${VENV_PATH}/bin/activate\` to activate it.\033[0m\n\n\n" -test: # Run test scripts. +lint-black: + @printf "Checking code style with black...\n" + black *.py --check --target-version=py36 + @printf "\033[1;34mBlack passes!\033[0m\n\n" + +lint-pylint: + @printf "Checking code style with pylint...\n" + pylint *.py --rcfile=.pylintrc + @printf "\033[1;34mPylint passes!\033[0m\n\n" + +lint: lint-black lint-pylint # Check code style with black and pylint. + +test: clean # Run test scripts. + @printf "Running test script...\n" ${SHELL} scripts/test.sh + @printf "\033[1;34mTests pass!\033[0m\n\n" + +check: clean lint test # Alias for `make clean lint test`. + +black: # Format code in-place with black. + black *.py --target-version=py36 publish: # Run notebook in-place and generate HTML files. jupyter nbconvert --to notebook --inplace --execute tests-as-linear.ipynb @@ -30,4 +49,4 @@ publish: # Run notebook in-place and generate HTML files. mv tests-as-linear.html index.html clean: # Clean directory. - rm -rf _site/ + rm -rf _site/ __pycache__/ diff --git a/index.html b/index.html index 9699e87..ccaea6f 100644 --- a/index.html +++ b/index.html @@ -13196,6 +13196,7 @@

Table of contents5.1.5 Python code: Mann-Whitney U +
  • 5.2 Welch’s t-test
    • @@ -13234,6 +13235,8 @@

    2 Settings and toy dataimport scipy import statsmodels.formula.api as smf import matplotlib.pyplot as plt +import plots +np.random.seed(1618) # Reproducible results plt.style.use('seaborn-whitegrid') @@ -13245,28 +13248,12 @@

    2 Settings and toy data
    In [3]:
    -
    -
    -
    # Reproducible results
-np.random.seed(1859)
-
-# TODO any plt stuff, possibly in a function?
-
    - -
    -
    -
    - - -
    -
    -
    In [4]:
    # Correlated data with fixed correlation
 correlated_data = pd.DataFrame()
-correlated_data["x"] = np.random.normal(0.5, 0.5, 30)
-correlated_data["y"] = 0.8 * correlated_data["x"] + 0.2 + 0.1*np.random.randn(30)
+correlated_data["x"] = np.random.normal(0.5, 0.5, 20)
+correlated_data["y"] = 0.9 * correlated_data["x"] + 0.2 + 0.1*np.random.randn(20)
 
 correlated_data.head()
    @@ -13281,7 +13268,7 @@

    2 Settings and toy data -
    Out[4]:
    +
    Out[3]:
    @@ -13311,28 +13298,28 @@

    2 Settings and toy data 0 - 0.240200 - 0.404321 + -0.290010 + -0.084340 1 - 0.874423 - 0.773233 + 0.917701 + 1.039325 2 - -0.205784 - -0.071019 + 0.817674 + 0.899141 3 - 0.291822 - 0.622727 + 0.089775 + 0.335860 4 - 0.971538 - 0.941467 + 0.300801 + 0.467720 @@ -13347,7 +13334,7 @@

    2 Settings and toy data
    -
    In [5]:
    +
    In [4]:
    data = pd.DataFrame()
@@ -13369,7 +13356,7 @@ 
    2 Settings and toy data
 
-    
    Out[5]:
    
+    
    Out[4]:
    
 
 
 
@@ -13401,38 +13388,38 @@ 
    2 Settings and toy data
     
       0
-      1.032769
-      -0.010210
-      1.671794
-      -1.682004
+      0.370360
+      0.634343
+      -0.111973
+      0.746316
     
     
       1
-      -0.063599
-      1.065212
-      1.987121
-      -0.921908
+      -1.403470
+      -0.556456
+      -0.304594
+      -0.251862
     
     
       2
-      -0.855739
-      0.554099
-      1.002813
-      -0.448714
+      0.006593
+      -0.183445
+      0.216582
+      -0.400027
     
     
       3
-      1.879184
-      0.579551
-      -0.034006
-      0.613557
+      -1.242953
+      -0.274897
+      0.194504
+      -0.469401
     
     
       4
-      0.782369
-      -2.315127
-      -0.553362
-      -1.761765
+      -0.504203
+      -0.639618
+      1.453154
+      -2.092772
     
   
 
@@ -13458,7 +13445,7 @@ 
    3 Pearson and Spearman correlation
 
    
 
    
-
    In [6]:
    
+
    In [5]:
    
 
    
     
    
 
    res = smf.ols(formula="y ~ 1 + x", data=correlated_data).fit()
@@ -13472,15 +13459,11 @@ 
    3 Pearson and Spearman correlation
 
    
 
    
-
    In [7]:
    
+
    In [6]:
    
 
    
     
    
-
    fig, ax = plt.subplots(figsize=[10, 8])
-ax.scatter(correlated_data["y"], correlated_data["x"], color="k")
-ax.axhline(intercept, color="b", label=r"$\beta_0$ (Intercept)")
-ax.plot(ax.get_xlim(), [slope*x + intercept for x in ax.get_xlim()],
-        color="r", label=r"$\beta_1$ (Slope)")
-ax.legend();
+
    plots.linear_regression_plot(correlated_data, intercept, slope)
+plt.show()
 
    
 
     
    
@@ -13499,7 +13482,7 @@ 
    3 Pearson and Spearman correlation
-3 Pearson and Spearman correlation
 
    
 
    
-
    In [8]:
    
+
    In [7]:
    
 
    
     
    
 
    ranked_data = np.argsort(correlated_data, axis=0)
@@ -13539,28 +13522,11 @@ 
    3 Pearson and Spearman correlation
 
    
 
    
-
    In [9]:
    
+
    In [8]:
    
 
    
     
    
-
    to_str1 = lambda x: "{:.1f}".format(x)
-to_str2 = lambda x: "{:d}".format(x)
-
-fig, axarr = plt.subplots(ncols=2, figsize=[18, 8])
-
-for ax, dataset, to_str, title, a, b in zip(axarr,
-                                            [correlated_data, ranked_data],
-                                            [to_str1, to_str2],
-                                            ["Pearson", "Spearman"],
-                                            [slope, slope_spearman],
-                                            [intercept, intercept_spearman]):
-    ax.set_title(title)
-    ax.scatter(dataset["y"], dataset["x"], color="k")
-    annotations = "(" + dataset["x"].apply(to_str) + ", " + dataset["x"].apply(to_str) + ")"
-    for i, annot in enumerate(annotations):
-        ax.annotate(annot, (dataset["y"][i], dataset["x"][i]), color="grey")
-    ax.axhline(a, color="b", label=r"$\beta_0$ (Intercept)")
-    ax.plot(ax.get_xlim(), [a*x + b for x in ax.get_xlim()], color="r", label=r"$\beta_1$ (Slope)")
-    ax.legend(fontsize="large")
+
    plots.pearson_spearman_plot(correlated_data, ranked_data, slope, slope_spearman, intercept, intercept_spearman)
+plt.show()
 
    
 
     
    
@@ -13579,7 +13545,7 @@ 
    3 Pearson and Spearman correlation
-
 
    
@@ -13601,7 +13567,7 @@ 
    3.0.2 Theory: rank-transformation
 
    
 
    
-
    In [10]:
    
+
    In [9]:
    
 
    
     
    
 
    def signed_rank(x, axis=-1):
@@ -13624,7 +13590,7 @@ 
    3.0.3 Python code: Pearson corre
 
    
 
    
 
    
-
    In [11]:
    
+
    In [10]:
    
 
    
     
    
 
    scaled_data = correlated_data / correlated_data.std()
@@ -13641,19 +13607,12 @@ 
    3.0.3 Python code: Pearson corre
 
    
 
    
 
    
-
    In [12]:
    
+
    In [11]:
    
 
    
     
    
-
    # Tabulate and display
-results = [res1, res2]
-df = pd.DataFrame(index=["scipy.stats.pearsonr", "smf.ols", "smf.ols (scaled)"])
-df["slope"] = [r] + [res.params.x for res in results]
-df["p-values"] = [p] + [res.pvalues.x for res in results]
-df["t-values"] = [None] + [res.tvalues.x for res in results]
-df["0.025 CI"] = [None] + [res.conf_int().loc["x", 0] for res in results]
-df["0.975 CI"] = [None] + [res.conf_int().loc["x", 1] for res in results]
-
-df
+
    utils.tabulate_results([r, p, None, None, None],
+                       [res1, res2],
+                       ["scipy.stats.pearsonr", "smf.ols", "smf.ols (scaled)"])
 
    
 
     
    
@@ -13666,7 +13625,7 @@ 
    3.0.3 Python code: Pearson corre
 
 
    
 
-    
    Out[12]:
    
+    
    Out[11]:
    
 
 
 
@@ -13689,7 +13648,7 @@ 
    3.0.3 Python code: Pearson corre
   
     
       
-      slope
+      value
       p-values
       t-values
       0.025 CI
@@ -13699,27 +13658,27 @@ 
    3.0.3 Python code: Pearson corre
   
     
       scipy.stats.pearsonr
-      0.979512
-      4.963806e-21
+      0.981042
+      2.804604e-14
       NaN
       NaN
       NaN
     
     
       smf.ols
-      0.847384
-      4.963806e-21
-      25.736805
-      0.779941
-      0.914828
+      0.861270
+      2.804604e-14
+      21.47749
+      0.777021
+      0.945520
     
     
       smf.ols (scaled)
-      0.979512
-      4.963806e-21
-      25.736805
-      0.901552
-      1.057471
+      0.981042
+      2.804604e-14
+      21.47749
+      0.885077
+      1.077008
     
   
 
@@ -13744,7 +13703,7 @@ 
    3.0.4 Python code: Spearman cor
 
    
 
    
 
    
-
    In [13]:
    
+
    In [12]:
    
 
    
     
    
 
    ranked_data = np.argsort(correlated_data, axis=0)
@@ -13760,18 +13719,12 @@ 
    3.0.4 Python code: Spearman cor
 
    
 
    
 
    
-
    In [14]:
    
+
    In [13]:
    
 
    
     
    
-
    # Tabulate and display
-df = pd.DataFrame(index=["scipy.stats.spearmanr", "smf.ols (ranked)"])
-df["slope"] = [r, res.params.x]
-df["p-values"] = [p, res.pvalues.x]
-df["t-values"] = [None, res.tvalues.x]
-df["0.025 CI"] = [None, res.conf_int().loc["x", 0]]
-df["0.975 CI"] = [None, res.conf_int().loc["x", 1]]
-
-df
+
    utils.tabulate_results([r, p, None, None, None],
+                       res,
+                       ["scipy.stats.spearmanr", "smf.ols (ranked)"])
 
    
 
     
    
@@ -13784,7 +13737,7 @@ 
    3.0.4 Python code: Spearman cor
 
 
    
 
-    
    Out[14]:
    
+    
    Out[13]:
    
 
 
 
@@ -13807,7 +13760,7 @@ 
    3.0.4 Python code: Spearman cor
   
     
       
-      slope
+      value
       p-values
       t-values
       0.025 CI
@@ -13817,19 +13770,19 @@ 
    3.0.4 Python code: Spearman cor
   
     
       scipy.stats.spearmanr
-      0.308565
-      0.097109
+      0.566917
+      0.009146
       NaN
       NaN
       NaN
     
     
       smf.ols (ranked)
-      0.308565
-      0.097109
-      1.716534
-      -0.059658
-      0.676788
+      0.566917
+      0.009146
+      2.919762
+      0.158991
+      0.974844
     
   
 
@@ -13857,12 +13810,12 @@ 
    4 One mean
 
    
 
    
-
    In [15]:
    
+
    In [14]:
    
 
    
     
    
-
    signed_rank_data = signed_rank(data, axis=0)
-res = smf.ols(formula="y ~ 1", data=signed_rank_data).fit()
-intercept_wilcoxon = res.params
+
    signed_rank_correlated_data = signed_rank(correlated_data, axis=0)
+res = smf.ols(formula="y ~ 1", data=signed_rank_correlated_data).fit()
+intercept_wilcoxon = res.params.Intercept
 
    
 
     
    
@@ -13872,26 +13825,11 @@ 
    4 One mean
 
    
 
    
-
    In [16]:
    
+
    In [15]:
    
 
    
     
    
-
    to_str1 = lambda x: "{:.1f}".format(x)
-to_str2 = lambda x: "{:d}".format(x)
-
-fig, axarr = plt.subplots(ncols=2, figsize=[18, 8])
-
-for ax, dataset, to_str, title, b in zip(axarr,
-                                         [data.y, signed_rank(data.y)],
-                                         [to_str1, to_str1],
-                                         ["$t$-test", "Wilcoxon"],
-                                         [intercept, intercept_wilcoxon]):
-    ax.set_title(title)
-    ax.scatter(np.ones(50), dataset, color="k")
-    annotations = dataset.apply(to_str)
-    for i, annot in enumerate(annotations):
-        ax.annotate(annot, (1, dataset[i]), color="grey")
-    ax.axhline(a, color="b", label=r"$\beta_0$ (Intercept)")
-    ax.legend(fontsize="large")
+
    plots.ttest_wilcoxon_plot(correlated_data, intercept, intercept_wilcoxon)
+plt.show()
 
    
 
     
    
@@ -13910,7 +13848,7 @@ 
    4 One mean
-4.1.2 Python code: One-sample $t
 
    
 
    
 
    
-
    In [17]:
    
+
    In [16]:
    
 
    
     
    
 
    t, p = scipy.stats.ttest_1samp(data.y, 0)
@@ -13945,19 +13883,13 @@ 
    4.1.2 Python code: One-sample $t
 
    
 
    
 
    
-
    In [18]:
    
+
    In [17]:
    
 
    
     
    
-
    # Tabulate and display
-df = pd.DataFrame(index=["scipy.stats.ttest_1samp", "smf.ols (y ~ 1)"])
-df["slope"] = [None, res.params.Intercept]
-df["p-values"] = [p, res.pvalues.Intercept]
-df["t-values"] = [t, res.tvalues.Intercept]
-df["df"] = [None, res.df_resid]
-df["0.025 CI"] = [None, res.conf_int().loc["Intercept", 0]]
-df["0.975 CI"] = [None, res.conf_int().loc["Intercept", 1]]
-
-df
+
    utils.tabulate_results([None, p, t, None, None],
+                       res,
+                       ["scipy.stats.ttest_1samp", "smf.ols (y ~ 1)"],
+                       x=False)
 
    
 
     
    
@@ -13970,7 +13902,7 @@ 
    4.1.2 Python code: One-sample $t
 
 
    
 
-    
    Out[18]:
    
+    
    Out[17]:
    
 
 
 
@@ -13993,10 +13925,9 @@ 
    4.1.2 Python code: One-sample $t
   
     
       
-      slope
+      value
       p-values
       t-values
-      df
       0.025 CI
       0.975 CI
     
@@ -14005,20 +13936,18 @@ 
    4.1.2 Python code: One-sample $t
     
       scipy.stats.ttest_1samp
       NaN
-      0.016092
-      2.493053
-      NaN
+      0.882318
+      0.148805
       NaN
       NaN
     
     
       smf.ols (y ~ 1)
-      0.369656
-      0.016092
-      2.493053
-      49.0
-      0.071687
-      0.667624
+      0.019429
+      0.882318
+      0.148805
+      -0.242953
+      0.281811
     
   
 
@@ -14041,7 +13970,7 @@ 
    4.1.3 Python code: Wilcoxo
 
    
 
    
 
    
-
    In [19]:
    
+
    In [18]:
    
 
    
     
    
 
    signed_rank_data = signed_rank(data, axis=0)
@@ -14058,19 +13987,13 @@ 
    4.1.3 Python code: Wilcoxo
 
    
 
    
 
    
-
    In [20]:
    
+
    In [19]:
    
 
    
     
    
-
    # Tabulate and display
-df = pd.DataFrame(index=["scipy.stats.wilcoxon", "smf.ols (y ~ 1, signed rank)"])
-df["slope"] = [None, res.params.Intercept]
-df["p-values"] = [p, res.pvalues.Intercept]
-df["t-values"] = [None, res.tvalues.Intercept]
-df["df"] = [None, res.df_resid]
-df["0.025 CI"] = [None, res.conf_int().loc["Intercept", 0]]
-df["0.975 CI"] = [None, res.conf_int().loc["Intercept", 1]]
-
-df
+
    utils.tabulate_results([None, p, None, None, None],
+                       res,
+                       ["scipy.stats.wilcoxon", "smf.ols (y ~ 1, signed rank)"],
+                       x=False)
 
    
 
     
    
@@ -14083,7 +14006,7 @@ 
    4.1.3 Python code: Wilcoxo
 
 
    
 
-    
    Out[20]:
    
+    
    Out[19]:
    
 
 
 
@@ -14106,10 +14029,9 @@ 
    4.1.3 Python code: Wilcoxo
   
     
       
-      slope
+      value
       p-values
       t-values
-      df
       0.025 CI
       0.975 CI
     
@@ -14118,20 +14040,18 @@ 
    4.1.3 Python code: Wilcoxo
     
       scipy.stats.wilcoxon
       NaN
-      0.017335
-      NaN
+      0.942284
       NaN
       NaN
       NaN
     
     
       smf.ols (y ~ 1, signed rank)
-      7.62
-      0.057262
-      1.947136
-      49.0
-      -0.244352
-      15.484352
+      -2.78
+      0.494895
+      -0.687683
+      -10.903825
+      5.343825
     
   
 
@@ -14156,7 +14076,7 @@ 
    4.2 Paired sampl
 
    
 
    
 
    
-
    In [21]:
    
+
    In [20]:
    
 
    
     
    
 
    # TODO
@@ -14175,19 +14095,6 @@ 
    4.2 Paired sampl
 
 
    
 
    
-
    
-
    
-
    
-
    In [22]:
    
-
    
-    
    
-
    # TODO
-
    
-
-    
    
-
    
-
    
-
 
    
 
    
 
    
@@ -14198,7 +14105,7 @@ 
    4.2.2 Python code: Paired sam
 
    
 
    
 
    
-
    In [23]:
    
+
    In [21]:
    
 
    
     
    
 
    t, p = scipy.stats.ttest_ind(data.y, data.y2)
@@ -14212,19 +14119,13 @@ 
    4.2.2 Python code: Paired sam
 
    
 
    
 
    
-
    In [24]:
    
+
    In [22]:
    
 
    
     
    
-
    # Tabulate and display
-df = pd.DataFrame(index=["scipy.stats.ttest_ind", "smf.ols (y_sub_y2 ~ 1)"])
-df["slope"] = [None, res.params.Intercept]
-df["p-values"] = [p, res.pvalues.Intercept]
-df["t-values"] = [t, res.tvalues.Intercept]
-df["df"] = [None, res.df_resid]
-df["0.025 CI"] = [None, res.conf_int().loc["Intercept", 0]]
-df["0.975 CI"] = [None, res.conf_int().loc["Intercept", 1]]
-
-df
+
    utils.tabulate_results([None, p, t, None, None],
+                       res,
+                       ["scipy.stats.ttest_ind", "smf.ols (y_sub_y2 ~ 1)"],
+                       x=False)
 
    
 
     
    
@@ -14237,7 +14138,7 @@ 
    4.2.2 Python code: Paired sam
 
 
    
 
-    
    Out[24]:
    
+    
    Out[22]:
    
 
 
 
@@ -14260,10 +14161,9 @@ 
    4.2.2 Python code: Paired sam
   
     
       
-      slope
+      value
       p-values
       t-values
-      df
       0.025 CI
       0.975 CI
     
@@ -14272,20 +14172,18 @@ 
    4.2.2 Python code: Paired sam
     
       scipy.stats.ttest_ind
       NaN
-      0.699144
-      -0.387612
-      NaN
+      0.119175
+      -1.571994
       NaN
       NaN
     
     
       smf.ols (y_sub_y2 ~ 1)
-      -0.079916
-      0.702639
-      -0.384001
-      49.0
-      -0.498137
-      0.338305
+      -0.278406
+      0.075029
+      -1.818975
+      -0.585985
+      0.029173
     
   
 
@@ -14308,7 +14206,7 @@ 
    4.2.3 Python code: Wilcoxon m
 
    
 
    
 
    
-
    In [25]:
    
+
    In [23]:
    
 
    
     
    
 
    # FIXME disagreement?
@@ -14323,19 +14221,13 @@ 
    4.2.3 Python code: Wilcoxon m
 
    
 
    
 
    
-
    In [26]:
    
+
    In [24]:
    
 
    
     
    
-
    # Tabulate and display
-df = pd.DataFrame(index=["scipy.stats.wilcoxon", "smf.ols (y_sub_y2 ~ 1)"])
-df["slope"] = [None, res.params.Intercept]
-df["p-values"] = [p, res.pvalues.Intercept]
-df["t-values"] = [None, res.tvalues.Intercept]
-df["df"] = [None, res.df_resid]
-df["0.025 CI"] = [None, res.conf_int().loc["Intercept", 0]]
-df["0.975 CI"] = [None, res.conf_int().loc["Intercept", 1]]
-
-df
+
    utils.tabulate_results([None, p, None, None, None],
+                       res,
+                       ["scipy.stats.wilcoxon", "smf.ols (y_sub_y2 ~ 1)"],
+                       x=False)
 
    
 
     
    
@@ -14348,7 +14240,7 @@ 
    4.2.3 Python code: Wilcoxon m
 
 
    
 
-    
    Out[26]:
    
+    
    Out[24]:
    
 
 
 
@@ -14371,10 +14263,9 @@ 
    4.2.3 Python code: Wilcoxon m
   
     
       
-      slope
+      value
       p-values
       t-values
-      df
       0.025 CI
       0.975 CI
     
@@ -14383,20 +14274,18 @@ 
    4.2.3 Python code: Wilcoxon m
     
       scipy.stats.wilcoxon
       NaN
-      0.881060
-      NaN
+      0.071808
       NaN
       NaN
       NaN
     
     
       smf.ols (y_sub_y2 ~ 1)
-      3.22
-      0.428812
-      0.797842
-      49.0
-      -4.890423
-      11.330423
+      -5.18
+      0.200729
+      -1.296931
+      -13.206335
+      2.846335
     
   
 
@@ -14413,13 +14302,6 @@ 
    4.2.3 Python code: Wilcoxon m
 
    
 
    
 
    For large sample sizes (N >> 100), this approaches the sign test to a reasonable degree, but this approximation is too inaccurate to flesh out here.
    
-
-
    
-
    
-
    
-
    
-
    
-
    
 
    5 Two means
    5.1 Independent t-test and Mann-Whitney U
    5.1.1 Theory: As linear models
    Independent t-test model: two means predict $y$.
    
 
    $y_i = \beta_0 + \beta_1 x_i \qquad \mathcal{H}_0: \beta_1 = 0$
    
 
    where $x_i$ is an indicator (0 or 1) saying whether data point $i$ was sampled from one or the other group. Indicator variables (also called "dummy coding")) underly a lot of linear models and we'll take an aside to see how it works in a minute.
    
@@ -14435,7 +14317,7 @@ 
    5.1.2 Theory: Dummy coding
 
    
-
    In [27]:
    
+
    In [25]:
    
 
    
     
    
 
    # TODO
@@ -14462,7 +14344,7 @@ 
    5.1.4 Python code: independent t-
 
    
 
    
 
    
-
    In [28]:
    
+
    In [26]:
    
 
    
     
    
 
    # TODO
@@ -14482,7 +14364,7 @@ 
    5.1.5 Python code: Mann-Whitney U
 
    
 
    
-
    In [29]:
    
+
    In [27]:
    
 
    
     
    
 
    # TODO
@@ -14492,6 +14374,27 @@ 
    5.1.5 Python code: Mann-Whitney U
 
    
 
+
    
+
    
+
    
+
    
+
    5.2 Welch’s t-test
    This is identical to the (Student's) independent t-test above except that Student's assumes identical variances and Welch's t-test does not. So the linear model is the same and the trick is in the variances, which I won't go further into here.
    
+
+
    
+
    
+
    
+
    
+
    
+
    In [28]:
    
+
    
+    
    
+
    t, p = scipy.stats.ttest_ind(data.y, data.y2, equal_var=False)
+
    
+
+    
    
+
    
+
    
+
 
    
     
    
   
    
diff --git a/plots.py b/plots.py
new file mode 100644
index 0000000..fe96198
--- /dev/null
+++ b/plots.py
@@ -0,0 +1,91 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from utils import signed_rank, format_decimals_factory
+
+
+def linear_regression_plot(data, intercept, slope):
+    fig, ax = plt.subplots(figsize=[10, 8])
+    ax.scatter(data["y"], data["x"], color="k")
+    ax.axhline(intercept, color="b", label=r"$\beta_0$ (Intercept)")
+    ax.plot(
+        ax.get_xlim(),
+        [slope * x + intercept for x in ax.get_xlim()],
+        color="r",
+        label=r"$\beta_1$ (Slope)",
+    )
+    ax.legend()
+
+    return fig, ax
+
+
+# pylint: disable=R0913,R0914
+def pearson_spearman_plot(
+    data_pearson,
+    data_spearman,
+    slope_pearson,
+    slope_spearman,
+    intercept_pearson,
+    intercept_spearman,
+):
+    fig, axarr = plt.subplots(ncols=2, figsize=[18, 8])
+
+    for ax, dataset, to_str, title, a, b in zip(
+        axarr,
+        [data_pearson, data_spearman],
+        [format_decimals_factory(), format_decimals_factory(0)],
+        ["Pearson", "Spearman"],
+        [slope_pearson, slope_spearman],
+        [intercept_pearson, intercept_spearman],
+    ):
+        # Plot
+        ax.scatter(dataset["y"], dataset["x"], color="k")
+
+        # Annotate data points
+        annotations = (
+            "(" + dataset["x"].apply(to_str) + ", " + dataset["x"].apply(to_str) + ")"
+        )
+        for i, annot in enumerate(annotations):
+            ax.annotate(annot, (dataset["y"][i], dataset["x"][i]), color="grey")
+
+        # Plot lines
+        ax.axhline(a, color="b", label=r"$\beta_0$ (Intercept)")
+        ax.plot(
+            ax.get_xlim(),
+            [a * x + b for x in ax.get_xlim()],
+            color="r",
+            label=r"$\beta_1$ (Slope)",
+        )
+
+        # Decorate
+        ax.set_title(title)
+        ax.legend(fontsize="large")
+
+    return fig, axarr
+
+
+def ttest_wilcoxon_plot(data, intercept_ttest, intercept_wilcoxon):
+    fig, axarr = plt.subplots(ncols=2, figsize=[18, 8])
+
+    for ax, dataset, to_str, title, b in zip(
+        axarr,
+        [data.y, signed_rank(data.y)],
+        [format_decimals_factory(), format_decimals_factory(0)],
+        ["$t$-test", "Wilcoxon"],
+        [intercept_ttest, intercept_wilcoxon],
+    ):
+        # Scatter plot
+        ax.scatter(np.ones_like(dataset), dataset, color="k")
+
+        # Annotate data points
+        annotations = dataset.apply(to_str)
+        for i, annot in enumerate(annotations):
+            ax.annotate(annot, (1, dataset[i]), color="grey")
+
+        # Plot lines
+        ax.axhline(b, color="b", label=r"$\beta_0$ (Intercept)")
+
+        # Decorate
+        ax.set_title(title)
+        ax.legend(fontsize="large")
+
+    return fig, axarr
diff --git a/requirements.txt b/requirements.txt
index b843e1e..ad37b91 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,8 +1,10 @@
-pandas==0.24.2
-patsy==0.5.1
+black==19.3b0
 jupyter==1.0.0
 matplotlib==3.1.0
 nbdime==1.0.6
 numpy==1.16.4
+pandas==0.24.2
+patsy==0.5.1
+pylint==2.3.1
 scipy==1.2.0
 statsmodels==0.9.0
diff --git a/tests-as-linear.ipynb b/tests-as-linear.ipynb
index d080b79..8b7e2cd 100644
--- a/tests-as-linear.ipynb
+++ b/tests-as-linear.ipynb
@@ -53,7 +53,8 @@
        "    - [5.1.2 Theory: Dummy coding](#5.1.2-Theory:-Dummy-coding)\n",
        "    - [5.1.3 Theory: Dummy coding (continued)](#5.1.3-Theory:-Dummy-coding-(continued))\n",
        "    - [5.1.4 Python code: independent t-test](#5.1.4-Python-code:-independent-t-test)\n",
-       "    - [5.1.5 Python code: Mann-Whitney U](#5.1.5-Python-code:-Mann-Whitney-U)\n"
+       "    - [5.1.5 Python code: Mann-Whitney U](#5.1.5-Python-code:-Mann-Whitney-U)\n",
+       "  - [5.2 Welch’s t-test](#5.2-Welch’s-t-test)"
       ],
       "text/plain": [
        ""
@@ -109,6 +110,8 @@
     "import scipy\n",
     "import statsmodels.formula.api as smf\n",
     "import matplotlib.pyplot as plt\n",
+    "import plots\n",
+    "np.random.seed(1618)  # Reproducible results\n",
     "plt.style.use('seaborn-whitegrid')"
    ]
   },
@@ -116,18 +119,6 @@
    "cell_type": "code",
    "execution_count": 3,
    "metadata": {},
-   "outputs": [],
-   "source": [
-    "# Reproducible results\n",
-    "np.random.seed(1859)\n",
-    "\n",
-    "# TODO any plt stuff, possibly in a function?"
-   ]
-  },
-  {
-   "cell_type": "code",
-   "execution_count": 4,
-   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -157,28 +148,28 @@
        "  \n",
        "    \n",
        "      0\n",
-       "      0.240200\n",
-       "      0.404321\n",
+       "      -0.290010\n",
+       "      -0.084340\n",
        "    \n",
        "    \n",
        "      1\n",
-       "      0.874423\n",
-       "      0.773233\n",
+       "      0.917701\n",
+       "      1.039325\n",
        "    \n",
        "    \n",
        "      2\n",
-       "      -0.205784\n",
-       "      -0.071019\n",
+       "      0.817674\n",
+       "      0.899141\n",
        "    \n",
        "    \n",
        "      3\n",
-       "      0.291822\n",
-       "      0.622727\n",
+       "      0.089775\n",
+       "      0.335860\n",
        "    \n",
        "    \n",
        "      4\n",
-       "      0.971538\n",
-       "      0.941467\n",
+       "      0.300801\n",
+       "      0.467720\n",
        "    \n",
        "  \n",
        "\n",
@@ -186,14 +177,14 @@
       ],
       "text/plain": [
        "          x         y\n",
-       "0  0.240200  0.404321\n",
-       "1  0.874423  0.773233\n",
-       "2 -0.205784 -0.071019\n",
-       "3  0.291822  0.622727\n",
-       "4  0.971538  0.941467"
+       "0 -0.290010 -0.084340\n",
+       "1  0.917701  1.039325\n",
+       "2  0.817674  0.899141\n",
+       "3  0.089775  0.335860\n",
+       "4  0.300801  0.467720"
       ]
      },
-     "execution_count": 4,
+     "execution_count": 3,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -201,15 +192,15 @@
    "source": [
     "# Correlated data with fixed correlation\n",
     "correlated_data = pd.DataFrame()\n",
-    "correlated_data[\"x\"] = np.random.normal(0.5, 0.5, 30)\n",
-    "correlated_data[\"y\"] = 0.8 * correlated_data[\"x\"] + 0.2 + 0.1*np.random.randn(30)\n",
+    "correlated_data[\"x\"] = np.random.normal(0.5, 0.5, 20)\n",
+    "correlated_data[\"y\"] = 0.9 * correlated_data[\"x\"] + 0.2 + 0.1*np.random.randn(20)\n",
     "\n",
     "correlated_data.head()"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 5,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -242,38 +233,38 @@
        "  \n",
        "    \n",
        "      0\n",
-       "      1.032769\n",
-       "      -0.010210\n",
-       "      1.671794\n",
-       "      -1.682004\n",
+       "      0.370360\n",
+       "      0.634343\n",
+       "      -0.111973\n",
+       "      0.746316\n",
        "    \n",
        "    \n",
        "      1\n",
-       "      -0.063599\n",
-       "      1.065212\n",
-       "      1.987121\n",
-       "      -0.921908\n",
+       "      -1.403470\n",
+       "      -0.556456\n",
+       "      -0.304594\n",
+       "      -0.251862\n",
        "    \n",
        "    \n",
        "      2\n",
-       "      -0.855739\n",
-       "      0.554099\n",
-       "      1.002813\n",
-       "      -0.448714\n",
+       "      0.006593\n",
+       "      -0.183445\n",
+       "      0.216582\n",
+       "      -0.400027\n",
        "    \n",
        "    \n",
        "      3\n",
-       "      1.879184\n",
-       "      0.579551\n",
-       "      -0.034006\n",
-       "      0.613557\n",
+       "      -1.242953\n",
+       "      -0.274897\n",
+       "      0.194504\n",
+       "      -0.469401\n",
        "    \n",
        "    \n",
        "      4\n",
-       "      0.782369\n",
-       "      -2.315127\n",
-       "      -0.553362\n",
-       "      -1.761765\n",
+       "      -0.504203\n",
+       "      -0.639618\n",
+       "      1.453154\n",
+       "      -2.092772\n",
        "    \n",
        "  \n",
        "\n",
@@ -281,14 +272,14 @@
       ],
       "text/plain": [
        "          x         y        y2  y_sub_y2\n",
-       "0  1.032769 -0.010210  1.671794 -1.682004\n",
-       "1 -0.063599  1.065212  1.987121 -0.921908\n",
-       "2 -0.855739  0.554099  1.002813 -0.448714\n",
-       "3  1.879184  0.579551 -0.034006  0.613557\n",
-       "4  0.782369 -2.315127 -0.553362 -1.761765"
+       "0  0.370360  0.634343 -0.111973  0.746316\n",
+       "1 -1.403470 -0.556456 -0.304594 -0.251862\n",
+       "2  0.006593 -0.183445  0.216582 -0.400027\n",
+       "3 -1.242953 -0.274897  0.194504 -0.469401\n",
+       "4 -0.504203 -0.639618  1.453154 -2.092772"
       ]
      },
-     "execution_count": 5,
+     "execution_count": 4,
      "metadata": {},
      "output_type": "execute_result"
     }
@@ -322,7 +313,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 5,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -332,14 +323,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 7,
-   "metadata": {
-    "scrolled": false
-   },
+   "execution_count": 6,
+   "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "
    "
       ]
@@ -351,12 +340,8 @@
     }
    ],
    "source": [
-    "fig, ax = plt.subplots(figsize=[10, 8])\n",
-    "ax.scatter(correlated_data[\"y\"], correlated_data[\"x\"], color=\"k\")\n",
-    "ax.axhline(intercept, color=\"b\", label=r\"$\\beta_0$ (Intercept)\")\n",
-    "ax.plot(ax.get_xlim(), [slope*x + intercept for x in ax.get_xlim()],\n",
-    "        color=\"r\", label=r\"$\\beta_1$ (Slope)\")\n",
-    "ax.legend();"
+    "plots.linear_regression_plot(correlated_data, intercept, slope)\n",
+    "plt.show()"
    ]
   },
   {
@@ -376,7 +361,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 8,
+   "execution_count": 7,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -387,12 +372,12 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 8,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "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\n",
+      "image/png": "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\n",
       "text/plain": [
        "
    "
       ]
@@ -404,25 +389,8 @@
     }
    ],
    "source": [
-    "to_str1 = lambda x: \"{:.1f}\".format(x)\n",
-    "to_str2 = lambda x: \"{:d}\".format(x)\n",
-    "\n",
-    "fig, axarr = plt.subplots(ncols=2, figsize=[18, 8])\n",
-    "\n",
-    "for ax, dataset, to_str, title, a, b in zip(axarr,\n",
-    "                                            [correlated_data, ranked_data],\n",
-    "                                            [to_str1, to_str2],\n",
-    "                                            [\"Pearson\", \"Spearman\"],\n",
-    "                                            [slope, slope_spearman],\n",
-    "                                            [intercept, intercept_spearman]):\n",
-    "    ax.set_title(title)\n",
-    "    ax.scatter(dataset[\"y\"], dataset[\"x\"], color=\"k\")\n",
-    "    annotations = \"(\" + dataset[\"x\"].apply(to_str) + \", \" + dataset[\"x\"].apply(to_str) + \")\"\n",
-    "    for i, annot in enumerate(annotations):\n",
-    "        ax.annotate(annot, (dataset[\"y\"][i], dataset[\"x\"][i]), color=\"grey\")\n",
-    "    ax.axhline(a, color=\"b\", label=r\"$\\beta_0$ (Intercept)\")\n",
-    "    ax.plot(ax.get_xlim(), [a*x + b for x in ax.get_xlim()], color=\"r\", label=r\"$\\beta_1$ (Slope)\")\n",
-    "    ax.legend(fontsize=\"large\")"
+    "plots.pearson_spearman_plot(correlated_data, ranked_data, slope, slope_spearman, intercept, intercept_spearman)\n",
+    "plt.show()"
    ]
   },
   {
@@ -438,7 +406,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 10,
+   "execution_count": 9,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -459,7 +427,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 11,
+   "execution_count": 10,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -472,7 +440,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 12,
+   "execution_count": 11,
    "metadata": {},
    "outputs": [
     {
@@ -496,7 +464,7 @@
        "  \n",
        "    \n",
        "      \n",
-       "      slope\n",
+       "      value\n",
        "      p-values\n",
        "      t-values\n",
        "      0.025 CI\n",
@@ -506,55 +474,48 @@
        "  \n",
        "    \n",
        "      scipy.stats.pearsonr\n",
-       "      0.979512\n",
-       "      4.963806e-21\n",
+       "      0.981042\n",
+       "      2.804604e-14\n",
        "      NaN\n",
        "      NaN\n",
        "      NaN\n",
        "    \n",
        "    \n",
        "      smf.ols\n",
-       "      0.847384\n",
-       "      4.963806e-21\n",
-       "      25.736805\n",
-       "      0.779941\n",
-       "      0.914828\n",
+       "      0.861270\n",
+       "      2.804604e-14\n",
+       "      21.47749\n",
+       "      0.777021\n",
+       "      0.945520\n",
        "    \n",
        "    \n",
        "      smf.ols (scaled)\n",
-       "      0.979512\n",
-       "      4.963806e-21\n",
-       "      25.736805\n",
-       "      0.901552\n",
-       "      1.057471\n",
+       "      0.981042\n",
+       "      2.804604e-14\n",
+       "      21.47749\n",
+       "      0.885077\n",
+       "      1.077008\n",
        "    \n",
        "  \n",
        "\n",
        "
    "
       ],
       "text/plain": [
-       "                         slope      p-values   t-values  0.025 CI  0.975 CI\n",
-       "scipy.stats.pearsonr  0.979512  4.963806e-21        NaN       NaN       NaN\n",
-       "smf.ols               0.847384  4.963806e-21  25.736805  0.779941  0.914828\n",
-       "smf.ols (scaled)      0.979512  4.963806e-21  25.736805  0.901552  1.057471"
+       "                         value      p-values  t-values  0.025 CI  0.975 CI\n",
+       "scipy.stats.pearsonr  0.981042  2.804604e-14       NaN       NaN       NaN\n",
+       "smf.ols               0.861270  2.804604e-14  21.47749  0.777021  0.945520\n",
+       "smf.ols (scaled)      0.981042  2.804604e-14  21.47749  0.885077  1.077008"
       ]
      },
-     "execution_count": 12,
+     "execution_count": 11,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Tabulate and display\n",
-    "results = [res1, res2]\n",
-    "df = pd.DataFrame(index=[\"scipy.stats.pearsonr\", \"smf.ols\", \"smf.ols (scaled)\"])\n",
-    "df[\"slope\"] = [r] + [res.params.x for res in results]\n",
-    "df[\"p-values\"] = [p] + [res.pvalues.x for res in results]\n",
-    "df[\"t-values\"] = [None] + [res.tvalues.x for res in results]\n",
-    "df[\"0.025 CI\"] = [None] + [res.conf_int().loc[\"x\", 0] for res in results]\n",
-    "df[\"0.975 CI\"] = [None] + [res.conf_int().loc[\"x\", 1] for res in results]\n",
-    "\n",
-    "df"
+    "utils.tabulate_results([r, p, None, None, None],\n",
+    "                       [res1, res2],\n",
+    "                       [\"scipy.stats.pearsonr\", \"smf.ols\", \"smf.ols (scaled)\"])"
    ]
   },
   {
@@ -572,7 +533,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 13,
+   "execution_count": 12,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -584,7 +545,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 14,
+   "execution_count": 13,
    "metadata": {},
    "outputs": [
     {
@@ -608,7 +569,7 @@
        "  \n",
        "    \n",
        "      \n",
-       "      slope\n",
+       "      value\n",
        "      p-values\n",
        "      t-values\n",
        "      0.025 CI\n",
@@ -618,45 +579,39 @@
        "  \n",
        "    \n",
        "      scipy.stats.spearmanr\n",
-       "      0.308565\n",
-       "      0.097109\n",
+       "      0.566917\n",
+       "      0.009146\n",
        "      NaN\n",
        "      NaN\n",
        "      NaN\n",
        "    \n",
        "    \n",
        "      smf.ols (ranked)\n",
-       "      0.308565\n",
-       "      0.097109\n",
-       "      1.716534\n",
-       "      -0.059658\n",
-       "      0.676788\n",
+       "      0.566917\n",
+       "      0.009146\n",
+       "      2.919762\n",
+       "      0.158991\n",
+       "      0.974844\n",
        "    \n",
        "  \n",
        "\n",
        "
    "
       ],
       "text/plain": [
-       "                          slope  p-values  t-values  0.025 CI  0.975 CI\n",
-       "scipy.stats.spearmanr  0.308565  0.097109       NaN       NaN       NaN\n",
-       "smf.ols (ranked)       0.308565  0.097109  1.716534 -0.059658  0.676788"
+       "                          value  p-values  t-values  0.025 CI  0.975 CI\n",
+       "scipy.stats.spearmanr  0.566917  0.009146       NaN       NaN       NaN\n",
+       "smf.ols (ranked)       0.566917  0.009146  2.919762  0.158991  0.974844"
       ]
      },
-     "execution_count": 14,
+     "execution_count": 13,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Tabulate and display\n",
-    "df = pd.DataFrame(index=[\"scipy.stats.spearmanr\", \"smf.ols (ranked)\"])\n",
-    "df[\"slope\"] = [r, res.params.x]\n",
-    "df[\"p-values\"] = [p, res.pvalues.x]\n",
-    "df[\"t-values\"] = [None, res.tvalues.x]\n",
-    "df[\"0.025 CI\"] = [None, res.conf_int().loc[\"x\", 0]]\n",
-    "df[\"0.975 CI\"] = [None, res.conf_int().loc[\"x\", 1]]\n",
-    "\n",
-    "df"
+    "utils.tabulate_results([r, p, None, None, None],\n",
+    "                       res,\n",
+    "                       [\"scipy.stats.spearmanr\", \"smf.ols (ranked)\"])"
    ]
   },
   {
@@ -684,23 +639,23 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 15,
+   "execution_count": 14,
    "metadata": {},
    "outputs": [],
    "source": [
-    "signed_rank_data = signed_rank(data, axis=0)\n",
-    "res = smf.ols(formula=\"y ~ 1\", data=signed_rank_data).fit()\n",
-    "intercept_wilcoxon = res.params"
+    "signed_rank_correlated_data = signed_rank(correlated_data, axis=0)\n",
+    "res = smf.ols(formula=\"y ~ 1\", data=signed_rank_correlated_data).fit()\n",
+    "intercept_wilcoxon = res.params.Intercept"
    ]
   },
   {
    "cell_type": "code",
-   "execution_count": 16,
+   "execution_count": 15,
    "metadata": {},
    "outputs": [
     {
      "data": {
-      "image/png": "iVBORw0KGgoAAAANSUhEUgAABAkAAAHeCAYAAAD5BFKxAAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nOzde3yU5Z3//9fkNDmAkEg4SEhiCdxiDAIRwXI0IJTDQqKI1hEkgKk9uN2vrT/bTb/d3W6zPWiX7m7X8MPmAJrSChokJARUTgVBBUEQwg0oOXCQghiUhMwkk/n+kTBmkmA9JJMw834+Hnk85r7v65p8ruQxmTufua7PZXG5XIiIiIiIiIiIBHR1ACIiIiIiIiLSPShJICIiIiIiIiKAkgQiIiIiIiIi0kxJAhEREREREREBlCQQERERERERkWZKEoiIiIiIiIgIoCSBiIiIiIiIiDRTkkBEREREREREACUJRK5LhmGcMgxjZFfHISIiIiIiviWoqwMQkS/HMIw+QD/gyDWubwYeMk3zwld8/q/VX0RERK5PhmFsBDaZpvn75uOhgAn82jTNnzaf6wucAnYB3wf6An8wTfO2rolaRDqaZhKIXEcMw0gAqmh67X5kGMZHhmG0Tvbd8zW/zdftLyIiItenjcDkFsf/ABQBc1qcSwF2maZ5t2ma7X5gISLXN80kELmOmKZ5wjCMHwMTTdN8oPV1wzDymh9uNQxjpmmaVYZh/APwMyAEqAV+DBwC8oAhQCOwD/gOkNO6f+eOSERERLqRjcC/GoYRYJpmI01Jgn8G/mwYxjdM0/wAmAIUG4ZRDsxr2dkwjB7A/wDjgAZgHZAJ3AD8LzACcDV/n3+m6T5kNzDJNM13DcNYBTSYprnYMIwJwNNAOOAAfmaaZqlhGIuANJruX4Y0X1tomuZ7nfMjEfE/mkkgcv25HTjQ3gXTNNObH97dnCAYAvwHMNM0zZFABvAycB/Q0zTNEcDo5j7faN2/00YgIiIi3Y5pmseBi8BwwzAiAQPYA5QAc5ubTQGKr/EUvwBCgWE0JQTGAZOA/wY+ApKAO2i6l/mxaZplwJPAKsMwljSf/75hGDcCa4EfmqY5HHgEeMEwjJubv88k4PHmJQ67mp9DRDqIkgQi158RwLtfsO09wADgdcMwDgAFNGXeDwCJhmFsA34C/N40zROdEKuIiIhcX64uOZgBvNo8o2ADMM0wjHiA5n/u2zMVyDFN02mapsM0zUmmaW5rfq4/mKbpMk3TDixvPodpms8BJ2iagTDPNM0rwBjghGmabza3OUxTMmBy8/fZZ5rmqebH7wBRHTR2EUHLDUSuK4ZhBAC30TyTwDCMX/DZOsH1pmn+vFWXQOD1lksTDMMYBJwBEmh6s00BXjMM43HTNNd27ghERESkm9sILAXqaFouALAFeI6mJMC1ZhFA0xID19WD5nuOWtp+MBkABDe3sQKDgWqaZhIcb6d9yz4O4EqL8y7A8veHJSJflGYSiFxfwpq/AgBM0/y5aZojmr+uJgicNL/x0vSmPs0wjFsADMOYCRwEHqOpJsFm0zSfAjbRlHxo3V9ERET8y1aaZi1Ooun+ANM0a2n6xP4HfH6S4DXgEcMwApr/+V/b4nm+bxiGpfl8BvBqc5+ngfeA6cAfDMOIo2mJg2EYxp00PUgEJgLbOnCcInINShKIXEdM06yhaYreEcMwTl2j2cvATsMwbmuenpdBU8Ghd4F/p2nmQT5NswyOGIaxl6aCQv/Vun/njURERES6o+bp/seaHpqXWlwqpqlQ4LbP6f5vNH3S/y6wHygxTfNl4B9p2irxUPOXCWQZhjEbSAV+YJrmIWAZsJqmWQX3A/9jGMYh4E9AummaxzpqnCJybRaXy/X3W4mIiIiIiIiIz9NMAhEREREREREBlCQQERERERERkWZKEoiIiIiIiIgIoCSBiIiIiIiIiDQL6qwn3rdvnyoiioiIXENycrL29fYC3Y+IiIhcW3v3I52WJGj+hp359F9ZWVkZw4YN6+owuoTGrrH7I38ev8bePce+b9++rg7Br+h+pPvR2DV2f+PPYwf/Hn93Hvu17ke03EBEREREREREACUJRERERERERKSZkgQiIiIiIiIiAihJICIiIiIiIiLNlCQQEREREREREUBJAhERERERERFppiSBiIiIiIiIiABKEoiIiIiIiIhIMyUJRERERERERARQkkBEREREREREmilJICIiIiIiIiKAkgQiIiIiIiIi0kxJAhER+VKqqqpYunQpo0ePZsKECbz00ktdHZKIiFxHampqWLZsGRcuXODs2bM899xz5OXlUVJSgsvl8mhbX1/Piy++SF5eHgUFBdTU1HRR1NLd6H6k8yhJIOInnE4nhYWF5OXl8dxzz2Gapsf13bt38+yzz5Kfn09+fj4XLlzookilu/vhD3/IuHHj2LNnD7/85S/Jzs7+Uv2feeYZ/vrXvwKQkpLCoUOH/m6fxYsXc/Hixa8Ub0e6GkdNTQ1Lly6lrq6uq0MSEbmuOJ1ONmzYQFBQEABFRUV861vfIj09ndDQ0DbvCXv37qVv376kp6dz++23s2PHjq4IW7oh3Y903v2IkgQifuLgwYOEhYWRnp7Oww8/TElJicf1s2fPkpqayqJFi1i0aBF9+vTpokilOzt69CjV1dWkp6cTGBgIQFRU1Bfuf+DAAU6cOMGECRO+1PfdtWvXl2rfWa7GERERwezZs/mv//qvLo5IROT6snnzZpKTk+nZsycAn3zyCYMGDQJg0KBBVFZWerSvrKwkISEBgISEBE6ePOndgKVb0v1I596PBHXos4lIt5WYmMitt94KgMvlIiDAM0d49uxZdu7cyeXLlxkyZMiX/qMpHW/VKsjN/XrPUVsbS3j4ta8vXgwLF37x53vnnXcYNWoUjY2NHDlyhF/96ld85zvf+cL9/+d//oeHH3643Wtvvvkmy5YtY9CgQRw/fhyHw8HPf/5zXnnlFQAeeeQRVqxYwYABA9iyZQvZ2dnU19cTGhrKU089hcPhICsri/DwcGpra/nlL3/J2rVrycvLIyAggMjISH7zm99cs//IkSN58803+e1vf0u/fv2oqqoiNDSUX//61wwePJif/vSnHnHMmDGDZ555hiVLliipJiLyOQoKCsjMzCQyMpLY2Fjmz5/vvhYZGUl5eTnx8fEcO3aM+vp6j752ux2r1QqA1WrVDK4uoPsR/7sf0UwCER9WUFBAfHw8iYmJDB06lLVr12K321mzZg0pKSkebRMTE5k9ezaPPPIIVVVVHDt2rIuilu7s6NGj3HbbbSxcuJD77ruPsLAw7rnnHgCefvppHnroIZ588sk2N3nQ9GnRvn37GDdu3DWf/+DBgyxevJh169Yxb948/vCHP/CrX/0KgJUrVzJgwADKy8tZtmwZK1asYN26dfz7v/87jz/+OFeuXOH48eP87ne/Y/369Zw6dYpnnnmGP/7xjxQVFZGSkkJ2dvY1+9fW1gJw5MgRFi9eTFFREffeey9PPvkkQJs4rFYro0aNYvv27R36MxYR8SUFBQVkZGRQUVHByJEjiYqKYsuWLVRVVVFYWMiUKVPYuXMnq1atIiIigrCwMI/+VqsVh8MBNCUMQkNDu2IY0s3ofqRz70c0k0DER119U776h6aiooIf/ehHVFVVMX36dJKSktxtXS4XY8eOdb/xDhkyhLNnzzJ06NAuiV2aLFz45bLq7Skrq2TYsGEdExBQVlbG3LlzWbhwIadOneLnP/85Tz/9NN/+9rc5d+4cf/rTn8jOzmbTpk3Mnj3bo29FRQXR0dGEhIRc8/lvuukmd7y33norhYWFbdrs2rWLv/3tbyxatMh9zmKxUFFRwYABAxg4cCDQ9AY/fvx4BgwYAOBuX1BQ0G7/q1Ncb7nlFu644w4A7rvvPn7xi1/w8ccfExkZ2SaW2NhYTX0VEfkcmZmZ7nuRvLw89/nvfOc7fPe73+X48ePce++9hIeHU1JSwpAhQzz6X/00d+DAgZw4cYLY2Fivxi+6H/HH+xElCUR8VMs3ZWhaszRv3jxeeeUVfvKTn3i0tdvtZGdn8/3vf5/g4GBOnjzJyJEjvR2ydHNOp5P333+fW2+9lYCAAGJjYxk1ahQfffQR77zzDuPHjwdgwoQJvPzyy23elAMCAnA6nZ/7PVp+QmSxWNpUuQZobGzkrrvu4ve//7373NmzZykvLye8xVzGwMBALBaL+7iuro7Tp09fs3/fvn3Zu3eve23jVS6Xq825lj+Tz7vJEBHxd61rDFxlt9uBpnXkq1atIjg4mPj4eHeS4Pnnn+ehhx5i9OjRrFu3jtzcXAIDA7nvvvu8Frt0T7ofaf9n0pH3I1puIOKjWr8pT5gwgbCwMG655Rb3DgYHDx5k3759hIaGkpKSwsqVK8nLyyM6OrpNJl/k5MmT1NXVsWPHDpxOJ2VlZaxdu5a0tDQ++eQTevToAUDPnj25dOlSm/6DBg3i4sWL7hvDLyMwMJCGhgYAxo4dy65du3j//fcB2L59O3PmzGnzvLfddhu7d+/mb3/7GwB//vOfefrpp/9u/6NHj3L06FEA/vKXvzBq1ChuuOGGNnEAnDp1iptvvvlLj0dExF9c65P/rVu30qdPHwzD4LHHHmPJkiVMmTLFfX3BggUEBgYSHBzM/fffz+LFi3nkkUfc7zXiv3Q/0vn3I5pJIOKjYmNjqaiocB+XlpZSWlpKXFycx3S/q26//XZuv/12b4Yo15kjR44wePBgfvOb3/CTn/yE2NhYfvaznzFixAgOHz7M5cuXAfj000/p1atXm/433HADycnJ7Nmzh0mTJn2p733PPffw0EMP8eyzzzJ06FB+8Ytf8MQTT+ByuQgKCiI7O7vNpwLx8fE8+eSTLF26FIDo6Gj+4z/+g379+rXb/2rWv0+fPvz+97/n9OnTREVF8dvf/rbdOOLj49m/fz9ZWVlfaiwiIv4kKyvLY/kjNP2dffTRR7lw4QLbtm1zv39UV1cTExPDvHnz3G3r6+spLCykpqaGkJAQUlNTiYiI8Po4pPvQ/YgX7kdcLlenfO3du9fVXR05cqSrQ+gyGrv/eOGFF1zh4eEuwP0VHh7ueuGFF7o6NK/zt999Sx059l//+teu5cuXX/P7PPnkky6Xy+XKzs52FRUVtdtu3759rkcffbTDYvo8X2Xse/bscc2aNesLtX3ppZdcv/71r7/093C5XK7m98hOew/Wl+5HujuN3b+88MILrri4OJfFYnHFx8e7nn76add///d/u86fP+9uU1tb68rOznZ98sknHn3feOMN19atW10ul8t16NAhV0lJiTdD7zD++HtvSfcjX05X349ouYGIj7LZbKxYsYK4uDgsFgtxcXGsWLECm83W1aHJdaqsrIzBgwe3e23YsGHceOONPPTQQxw/fpxp06a1227UqFHcfPPN7NixozND7XSXL19mw4YNPP74410diohIt2ez2SgvL+fw4cM8++yzpKam0rNnT48227Zt484772xzvrKykoSEBAASEhJULFZ0P9JCZ92PaLmBiA+z2WzYbDbKyso6tKKs+KejR49+7nq3p5566gs9z9X9fbujMWPGsGHDhr/brkePHuR+3U2jRUT8REFBAZmZmURGRhIbG8v8+fM9rtfU1HDy5EmmT5/epq/dbsdqtQJN2yHW1dV5JWbpvnQ/8pnOuh9RkkBERL6QPXv2dHUIIiJynWm5JXNKSgoul4vt27czcOBA1qxZw3333cdLL72Ew+EgPz+f1NRUoqKi3P2tVitbtmzh8uXLWCwWgoODu3A00h3ofqTzKUkg4iecTifr16+nurqahoYGJk6ciGEYbdoVFRURFhbG1KlTuyBKERER8SUtt2TOy8sjICCA+++/n379+jF16lTeeOMNgoKCSE1Npa6ujgsXLrRJEnz44Yc89thjbN++nf3793fVUET8hmoSiPiJgwcPEhYWRnp6Og8//DAlJSVt2uzdu9e9PYuIiIjI19V6S+Zp06axd+9e9/ZtVVVVXLp0idLSUg4dOkR8fDwAzz//vHvv96CgIHJzcykvL/fY9k1EOoeSBCJ+IjExkbvvvhto2tUkIMDz5V9VVcXp06dJTk7uivBERETEB8XGxrofjxgxgtraWt5//30+/vhjIiMjqa6uZsqUKaSnp9OrVy927doFwIIFC9x7wU+aNInFixfzyCOPEBgYSGNjY1cNR8QvaLmBiJ8ICQkBmgoArVmzhpSUFPe1Tz/9lO3bt/PAAw9w+PDhrgpRREREfMzMmTPJzs4GYOTIkbhcLhISEujfvz8vvvgiAFu2bOHdd9/F4XDQ2Njo/lADIDg4mO3bt7Nz505CQkJwOp1tPugQkY6lV5iIDysoKCA+Pp7ExETi4+PJz89n5cqVDB8+nKSkJHe7I0eOUFtbS0FBATt37uTQoUMcOHCgCyMXERERX9ByeWNeXh6rVq2ipqYGp9PJPffcQ9++fYmLi2PRokUMHz6cb3zjGx797XY7DQ0NpKenExMTQ1CQPuMU6Wx6lYn4qJbVhAEuXLjAO++8Q1JSEiNHjvRoO2bMGMaMGQPAgQMHuHDhAiNGjPB6zCIiIuJbrlWT4OoWdtHR0Rw/fpxf/epXWK1WFi9eDEBhYSEpKSnY7XZ69+5NTk4OjY2NmkUg4gVKEoj4qJbVhAEmTJiA1Wpl37597u2DRo0aRX19veoQiIiISKeIjY2loqICaL8mwc0338zYsWO56aab2LFjB2+99RbTpk0jLS0NaJpJMGPGDKKjo3G5XCxbtqwrhyPiF5QkEPFRrTP3paWllJaWYrFYWL58+TX7aQaBiIiIdJSsrCzS09Opr6931yQYPHgwAwcOpLCwkG9/+9v06NEDgGHDhrFx40aP/larFYfDATQlDEJDQ70+BhF/o/k6Ij6qZTXhL3JeREREpDNYLBagqSZBfn4+BQUFhISEkJaWxp///GdOnz4NwAcffMCAAQM8+g4aNIjjx48DcOLECd3HiHiBkgQiPiorK4vw8HCPc+Hh4WRlZXVRRCIiIuJvMjMz3TMBrnI4HJw8eRKAWbNmsWnTJvLz86mqqmLixIkAPP/88zidTkaPHs358+fJzc1l3759TJ482dtDEPE7Wm4g4qNsNhvQ9OZcWVlJbGwsWVlZ7vMiIiIina318serVqxY4V7+eLVYYUsLFiwAIDAwkPvvv7/zAhSRNpQkEPFhNpsNm81GWVkZQ4cOZf369eTl5dHQ0MDEiRMxDMPd9tChQ7z55psEBATQt29fZs2a5Z4eKCIiIvJVtCxceFVERATf+973uHDhAi6Xi6KiIgCioqKYM2eOxw4GLpeL4uJizp07R2BgIHPmzCEqKsqrYxDxN1puIOInDh48SFhYGOnp6Tz88MMe+xbX19ezdetWHnnkERYvXozdbufYsWNdGK2IiIj4gtbLHwMCApg7dy69e/cG4PXXX2fKlCnu2QSmaXr0P3r0KA0NDSxZsoSpU6eyefNm7wUv4qc0k0DETyQmJnLrrbcCTVn5lln6oKAgFi9e7N4asbGxkaAg/XkQERGRr6f18sd58+YxadIkQkJCAJg/fz4BAQE4nU4uX77cZveCyspKEhISAIiJieHMmTPeHYCIH9JMAhEfVlBQQHx8PImJiQwdOpS1a9dit9tZs2YNKSkp7nYWi8W9/dCbb76Jw+HgG9/4RleFLSIiIj7EZrNRXl7Ohg0b+P73v09GRob7WkBAANXV1Tz77LPU1tbSr18/j752ux2r1eo+tlgsNDY2ei12EX+kjwpFfFRBQQEZGRnU1tYCUFFRwY9+9COqqqqYPn06SUlJHu1dLhevvvoqH330EfPnz1c9AhEREekQBQUFZGZmkpKSgtVqZffu3bhcLgoLC/n2t79N7969efzxx3nnnXfYvHkzqamp7r5Wq9Vjd4TWsyFFpOMpSSDiozIzM90JAmgqEjRv3jxeeeUVfvKTn7RpX1RURFBQEA8++KASBCIiItIhWn5okZeXB0CfPn34wQ9+wOTJk1mzZg319fWEhIRw5coVoqOjPfrHxMSwdetW9uzZQ0NDA5GRkV0xDBG/oiSBiI9qveXQhAkTCAsL45ZbbiE/Px+AUaNGUV9fz0033cT+/fuJi4tj5cqVAIwZM4Zhw4Z5O2wRERHxIa0/tAgICGDKlCk0NDQA4HA4cLlc7g8ori4tKCwsJCUlxeODC6fTqVkEIl6gJIGIj2q95dDmzZsJCwujX79+1NfXt9kC8V/+5V+or6/n+eefZ86cOfTp06crwhYREREf0vpDi2nTprF3717CwsKIjIzkoYceomfPngC89dZbfPrppwCkpaUBsGfPHiZPnsxtt90GwH/+5396MXoR/6RUnIiPar3l0PDhw6mvr2f8+PFttkAEOHPmDHl5eVy8eNHboYqIiIiPio2NdT8eMWIEtbW1vP/+++4ZA1cTBFVVVbz99tuMHTvWo78KF4p4n5IEIj7KZrOxYsUK4uLisFgsfPrpp8yfPx+bzdZu0Z+GhgYeeOABzSAQERGRDjNz5kz345EjR/KNb3yDxYsX079/f1588UUuX77Me++9x+rVq0lKSiIiIsKjf0hICHv27CEnJ4f8/HwtORDxAr3CRHzY1S2HDh8+zIkTJ1iwYEG7WyBCU6a/V69eXRSpiIiI+KKWMxfz8vJYtWoVNTU1OJ1O7rnnHsrKyiguLsZqtXrMgLwqICCAjz/+mCVLljB8+HBvhi7it5QkEPFhBQUFxMfHk5iYSHx8PPn5+axcuZLhw4e32QJRREREpKNdqyZBQ0MDjY2NvPbaa4SHh+Nyudi9ezdbt24FmgoXXrp0icbGRnr37k1OTg779+/viiGI+B0VLhTxUS23HAK4cOEC77zzDklJSYwcObKLoxMRERF/0LKQcsuaBB9//DE33ngjP/3pTwHYtm0bPXr04I477gA+K1zocDi46667GDJkCADLli2jsbFRSw5EOpGSBCI+qvWWQxMmTMBqtbJv3z6Cg4OBz7ZATE5O7qowRURExIfNnDmT7OxsoKkmgcvlIiEhgf79+7NmzRpmz57Nq6++yqVLl+jduzfJycke2x4GBwezfft2du7cSUhIiBIEIl6gJIGIj2o9va+0tJTS0lIsFgvLly+/Zr9FixZ1cmQiIiLiL1rXJAgICOD+++/H6XQydepUdu7cSUpKCuXl5Zw8eZKjR48ybNgwdx+73U5DQwNLly5l+/btnD9/viuGIeJXlIYT8VEttxz6IudFREREOtrn1SQAOHv2LHFxcQBER0fzwQcfAJ/VJKirqyMyMpKcnByOHTumWQQiXqCZBCI+Kisry6MmAUB4eDhZWVldGJWIyNdjGEZfYB9wD9AA5AMu4D3g+6ZpagN1kW7k82oSREZG4nK5sFgsTJ48mZMnT7qLE7asSTBjxgyio6NxuVwsW7asy8Yi4i+UJBDxUTabDWiqTVBZWUlsbCxZWVnu8yIi1xvDMIKB/x+40nzqP4Gfmaa5zTCM5cBcoLCr4hORttqrSTB69Gh69OjBc889h8Ph4OzZs2zYsAGHw0FAQIA7cQBgtVqpra3lxRdf5NNPP8Vut1NTU0NERERXDkvEp2m+jogPs9lslJeXc/jwYcrLy5UgEJHr3TPAcuBM83EysL358UZgalcEJSLX1romwZ49ezhx4gQffvghM2fOJCIigpdeeolvfetbxMXFERUVxaFDh9x9Bg0axI4dO+jbty9jxoxh4MCB7NixoyuGIuI3NJNAREREuj3DMBYB503T3GQYxk+bT1tM03Q1P/4U6NVe37KyMi9E+OXV1dV129g6m8buP2NvXZPg6NGjHDt2jIULF/L+++/Tu3dvzpw5wyuvvELPnj0ZOHAg7777Lm+88Qbjx4+nZ8+enDlzho8++gir1cqoUaN44403iI+P75oBfUX+9ntvzZ/Hfz2OXUkCET/hdDpZv3491dXVNDQ0MHHiRAzDcF83TZMdO3YQEBDAiBEjtC2iiHQ3iwGXYRhTgRHAKqBvi+s9ger2OraslN6dlJWVddvYOpvG7j9jb1mT4KrGxkYaGhowTZP58+ezbds2pkyZQnx8PMXFxfTo0YMFCxa42+/fv9+jLsGuXbuuu5+hv/3eW/Pn8Xfnse/bt6/d81puIOInDh48SFhYGOnp6Tz88MMe0/+cTiebNm3i4YcfZtGiRbzzzjtcvny5C6MVEfFkmuZE0zQnmaY5GTgALAQ2GoYxubnJDOCvXRSeiFzDzJkz2z3fs2dPHn/8cYqKipg1axY7d+5k1apVREREEBYW5tHWarXicDiApi0RQ0NDOz1uEX+mJIGIn0hMTOTuu+8GwOVyeWwhdOHCBaKioggLCyMwMJBBgwa1yfqLiHRDPwL+zTCM3UAIsLaL4xGRVlp+KAEwfPhwxo8fT0lJCcHBwVgsFo4dO8a9997LwoULqa2tZfDgwR59Bg0axPHjxwE4ceKEtnMW6WRfablBc3XhXCAesAK/NE1zfQfGJSIdLCQkBGjKwK9Zs4aUlBT3tdZZeavVit1u93qMIiJfRPNsgqsmdVUcIvL3ta5JUFZWRmpqKkOGDOGFF15g+vTpWCwWVq1aRXBwMPHx8QwZMgSA559/noceeojRo0ezbt06cnNzCQwM5L777uuKoYj4ja9ak+Bh4CPTNBcYhhFF07Q/JQlEupmCggKPLRD/9V//FYfDwejRo0lKSnK3a50U0FQ+ERER6QitaxLU19ezZs0a4uLiyM3NdZ9vWSfpqqt1CQIDA7n//vs7P1gRAb56kmANn03pswAN7TXqrlUcr8cKkx1FY/efsW/YsIGf//zn1NXVAU1LCvbt28fAgQMJDQ31+Fk0Njby4YcfcuDAAYKCgjh27BjR0dE+8/Pyt999Sxq7f45dRKS7yMrKIiMjg9raWgAsFgtpaWnceeed5ObmMnv2bHbs2OGuhVRdXU1MTAzz5s1zP0d9fT2FhYXU1NQQEhJCamoqERERXTIeEX/wlZIEpmleBjAMoydNyYKftdeuu1Zx7M4VJjubxu4/Y58xY4Y7QQAwYcIEQkNDKS8v58033wRg1KhR1NfXk5ycTFBQEDt27MseU4cAACAASURBVMDlcjF27Fif2t3A3373LWns3XPs16omLCLia2w2G4B7ZuP48eMZN24cTzzxBOXl5WzZsoUHH3wQgCtXrrBy5UqmT5/u8Rx79+6lb9++TJ48mffee48dO3YwY8YMr49FxF985S0QDcMYBBQCz5qm+aeOC0lEOkLrNYClpaWUlpZisVhYvnx5m/aGYbQ71U9ERETk67DZbNhsNnfytrGxEWiaNdByeeO2bdu488476dmzp0f/yspKxo0bB0BCQgI7duzwXvAifugr7W5gGEY/YDPwlGmauX+vvYh437Uq/6oisIiIiHhTQUEB8fHxJCYmEh8fz+rVq1m3bh0bN25010iqqanh5MmTjBgxok1/u92O1WoFmuootZwpKSId76tugfjPQCTwfw3D2Nb8Ffb3OomI92RlZREeHu5xLjw8nKysrC6KSERERPxNQUEBGRkZVFRU4HK5qKys5OWXX8Y0Tfr06cO6dev4+OOPWbVqFQ6Hg/z8fC5evOjxHCEhIWzZsoWcnBzy8vIIDg7uotGI+IevWpPgh8APOzgWEelArdcAxsbGkpWV5T4vIiIi0tkyMzPdRQsBpk2bRp8+fcjOzmbz5s2sWbOGrVu3EhQURGpqKnV1dVy4cIGoqCh3H6vVyrlz53jsscfYvn07+/fv74qhiPiNrzqTQESuAzabjfLycg4fPkx5ebkSBCIiIuJVrWskbdmyhY8//piUlBRKS0uJiYnh9OnTXLp0iU2bNnHo0CHi4+MBeP7553E6nYSGhhIUFERubi7l5eU4nc4uGImI/1CSQEREREREOkXrWkj19fWsWbOG+vp6ampqGD9+PNXV1UyZMoVFixbRq1cvdu3aBcCCBQsIDAykvr6eSZMmsXjxYh555BECAgLcxQ9FpOMpSSAiIiIiIp1i5syZ7Z7v2bMnjz/+OEVFRYSGhrp3WBo6dChnzpzxaGu1WnE4HO5jl8tFQID+jRHpLHp1iYiIiIhIpygpKfE4Hj58OOPHj6ekpITg4GAsFgtxcXEcP34cgIqKCqKjoz36DBo0yH391KlT9OvXzzvBi/ipr1S4UERERERE5O9pXZOgrKyM1NRUhgwZwgsvvMD06dPp378/RUVF7N27l9DQUO69914ACgsLSUlJYdiwYXzwwQfk5OQAMHfuXK+PQ8SfKEkgIiIiIiKdIjY2loqKCvfx1ZoEcXFx5Obmus8vWLCgTd+0tDT349mzZ3duoCLipuUGIiIiIiLSKbKysggPD3cfWywW7r33Xr773e+Sm5vL3/72N/e1Q4cOuWcLtORyudiwYQM5OTnk5+dz8eJFr8Qu4q+UJBARERERkU5hs9lYsWIFcXFxWCwWxo8fz7hx43jqqadISUlhy5YtAJw9e5b9+/fjcrnaPMfRo0dpaGhgyZIlTJ06lc2bN3t7GCJ+RcsNRPzMqVOneO2111i0aJHH+YMHD7J7924CAgIYMWIEo0eP7poARURExKfYbDZsNhtlZWUMGzbMvX1hdXU1oaGh1NbWsmXLFqZPn05RUVGb/pWVlSQkJAAQExPTZvcDEelYmkkg4kd27dpFUVERDQ0Nba69+uqrLFy4kMWLF7N7926uXLnSBRGKiIiIrykoKCA+Pp7ExETi4+NZvXo169atY+PGjdx2222sX7+eadOmYbVa2+1vt9s9rlksFneiQUQ6npIEIn4kMjKSiRMncv78eY/zly9fpqGhgYKCAlauXEl1dTUHDhzooihFRETEVxQUFJCRkUFFRQUul4uKigoyMjKoqanh8ccf5y9/+Qvnzp2juLiYtWvXcv78eUpLSz2ew2q14nA43Mcul4uAAP0bI9JZ9OoS8WGtM/dbtmxh69atbdb79ejRgxEjRvDRRx/x0Ucf0aNHD8aMGdNFUYuIiIivyMzMpLa21n08fPhwRo0aRWZmJsHBwfTo0YPvfe97LFq0iHnz5hEdHc23vvUtj+cYNGgQx48fB5qWTfbr18+rYxDxN0oSiPio9jL3OTk57U7lO3fuHMePH+cf//Ef6dWrF/3796esrKwLohYRERFfUllZ6XFcVlbGgAEDSElJ4YUXXmD69OkEBwe327ewsJBLly4xbNgwgoKCyMnJYdOmTUyfPt0boYv4LRUuFPFRrTP3AAcOHOC5554jNTXV47zVaiU4OJjy8nL69u2L1Wqlrq7Om+GKiIiID4qNjaWiosJ9XF9fz5o1a4iLiyM3N9ejbe/evVm6dKn7OC0tzf149uzZnR+siABKEoj4rJZvyC2dO3fO/fjQoUM4HA6Sk5NJTk5m/fr13HDDDQwYMIARI0Z4K1QRERHxUVlZWWRkZLg/uLBYLKSlpXHnnXeSm5vL7NmzaWxsZOPGjVgsFoKCgkhNTaVHjx7u53C5XBQXF3Pu3DkCAwOZM2cOUVFRXTUkEZ+nJIGIjwoMDMTpdLY5f/nyZfr27QtAUlKS+/wdd9zBrl27eOyxx7BYLF6LU0RERHyXzWYDmmY4VlZWMn78eMaNG8cTTzxBeXk5W7Zsoa6ujhkzZtC/f3/27t3Lrl27PJYUHD16lIaGBpYsWcKpU6fYvHkzDz74YFcNScTnKUkg4qPaSxAAHlsGtZxJUFNTg9VqVYJAREREOpTNZsNms1FWVsawYcPc9yLV1dWEhoYya9YsevbsCTTdpwQFef6LUllZSUJCAgAxMTGcOXPGuwMQ8TMqXCjio+Li4to936tXL/d6v6SkJJKTkwGIiIjgscce81p8IiIi4h9a77a0evVq1q1bx8aNG0lKSnInCKqqqnj77bcZO3asR3+73e5ReNlisXh86CEiHUtJAhEflZWVRXh4uMe58PBwsrKyuigiERER8Tetd1uqrKzk5ZdfxjRN+vTpw7p163A4HLz33nusXr2apKQkIiIiPJ4jJCSE3bt3k5OTQ35+Pk6nk4AA/Rsj0ln06hLxUTabjRUrVhAXF4fFYiEuLo4VK1a41waKiIiIdLbWuy1Nnz6dPn36kJ2dzaRJk7Db7Rw4cIDi4mJCQkLafMABTXWWqqurWbJkCcOHD/dm+CJ+SUkCER9ms9koLy/n8OHDlJeXK0EgIiIiXlVZWelx/Prrr/Pxxx+TkpJCaWkpAwcOZMuWLe7kwO7du9m6dSsAhYWFXLp0CafTSe/evcnJyWH//v24XC6vj0PEn6hwoYiIiIiIdIrY2FiPbZnr6+tZs2YNDz/8MDU1NcyaNYvBgwcDsG3bNnr06MEdd9wBQFpaGgAOh4O77rqLIUOGALBs2TIaGxu15ECkk+iVJSIiIiIinSIrK4uQkBD3scViIS0tjdtuu81dk+DcuXPk5uayf/9+Dh061GamQHBwMNu3bycvL4+CggIlCEQ6mV5dIn7m1KlT5Ofntzl/+vRp8vLyyM3N5cUXX6ShocH7wYmIiIjPaflP//Tp0+nbty8xMTHumgSvvfYaKSkpjBw5EoCjR4969Lfb7TQ0NJCenk5MTAyBgYFejV/E3yhJIOJHdu3aRVFRUZsEgMvloqioiLlz57J48WISEhKorq7uoihFRETEV2RmZlJfX+8+fv3117l48SI7d+501yQ4d+6ce+vm6OhoPvjgA+CzmgR1dXVERkaSk5PDsWPHNItApJPpFSbiRyIjI5k/f36b8x999BHh4eHs3r2b/Px8rly5Qp8+fbogQhEREfElrQsXXq1J8OGHH1JTU8P48eNxuVxYLBYmT55MYmIidrsdaKpJ0KtXLxwOBykpKSxZsoSlS5dqtqNIJ1PhQhEfVlBQQGZmJpWVlcTGxpKVlcWsWbPatKutraWqqooZM2YQFRXF6tWruemmm7j55pu7IGoRERHxFa0LFwYEBDB37lz69etHVFQUL7/8Mg0NDTz33HMEBQUREhJC7969PZ4jODiYkpISGhsb3W1EpPNoJoGIjyooKCAjI4OKigpcLhcVFRVkZGSwbt26Nm3Dw8OJiooiOjqawMBABg8ezJkzZ7ogahEREfElM2fO9DieNWsWkZGRWCwWHnjgAa5cuQLA7bffTnp6OpcvX8ZisbR5HpfLRXp6On369FFNApFOpiSBiI/KzMyktrbW41xtbS3PPPNMm7aRkZE4HA4uXrwINE0NjI6O9kqcIiIi4rtKSko8jl9//XVqampwuVy8+OKLhIeHExQUxJEjR8jJySE8PByn0wnA888/735ssVjIzc3lww8/dJ8Tkc6h5QYiPqr1GsCrnE4n58+fB+DQoUM4HA6Sk5NJSEggOzubgIAArFYrU6ZM8Wa4IiIi4oNa34/U1tbyl7/8BavVytixY5k+fTpvvfUWkydPJj4+nuLiYhwOBwALFiwAmuoYzJw5k+joaFwuF8uWLfP6OET8iZIEIj6q9RpAgHHjxnHHHXe4ZwkkJSW5r9ntdtLT07npppu8GqeIiIj4rvbuR2644QYWLlzI8OHDSUpKYsCAAZSWlrJjxw5iY2PbLCewWq3uxIHdbic0NNRr8Yv4Iy03EPFRWVlZhIeHe5yrqanh9ttvb7f92bNn2blzJ7m5ufz1r3/1RogiIiLi41rXJIiIiGDBggUEBgYycuRIAI4fP869997LwoULqa2tZfDgwR59Bg0axPHjxwE4ceIEsbGx3glexE8pSSDio2w2GytWrCAuLg6LxUJcXBw//vGPSUtLa7d9YmIis2fP5pFHHqGqqopjx455OWIRERHxNa1rEkyYMIGwsDDq6urIz88nPz+fqKgoVq1aRU5ODlarlSFDhgCf1SQYPXo058+fJzc3l3379jF58uQuGImI/9ByAxHB5XIxduxY9/S9IUOGcPbsWYYOHdrFkYmIiMj1rHVNgtLSUkpLS7FYLCxfvtx93jCMNn2v1iQIDAzk/vvv79xARcRNMwlEfNSX2QLRbreTnZ2Nw+HA5XJx8uRJ1SYQERGRr+1aSwO0ZECk+1KSQMRHXWsLxJycHI/dDfbt20doaCgpKSmsXLmS3/3ud1y+fNk91U9ERETkq2qvRlJ4eDhZWVldFJGI/D1abiDio9rbAnHcuHEkJSW1u7vB7bffTn19Pe+++66y+yIiItIhbDYb0PThRWVlJbGxsWRlZbnPi0j3o5kEIj6qvX/0L168yM6dO9ttX1VVxenTp0lOTu7s0ERERMSP2Gw2ysvLOXz4MOXl5UoQiHRzShKI+KisrCxCQkI8zr3//vs88cQTbdp++umnbN++vc02RSIiIiIi4l+03EDEh7lcrs89vurIkSPU1tZSUFDA5cuXqa+vp0+fPowYMcIbYYqIiIifcDqdrF+/nurqahoaGpg4cSIxMTEUFRVx5coVXC4XqampREVFufu4XC6Ki4s5d+4cgYGBzJkzx+O6iHQsJQlEfFRmZib19fUe5+rr63nmmWf4p3/6J4/zY8aMYcyYMQAcOHCACxcuKEEgIiIiHe7gwYOEhYWRlpbGlStXWL58OTfffDNJSUkkJiZy8uRJLly44JEEOHr0KA0NDSxZsoRTp06xefNmHnzwwS4chYhv03IDER/VXuFCgNOnT7sfX93dQERERMQbEhMTufvuu4GmGQIBAQFUVVXxySefsGrVKg4dOkR8fLxHn8rKShISEgCIiYnhzJkz3g5bxK8oSSDio661Q0GvXr1YunQp0LS7QetChSNGjGDq1KmdHp+IiIj4h4KCAuLj40lMTGTo0KGsXbsWu93OmjVrSElJobq6mtDQUBYuXEivXr3YtWuXR3+73Y7VanUfWywWGhsbvT0MEb+hJIGIj9K+xCIiItLVCgoKyMjIoKKiApfLRUVFBT/60Y9YtmwZw4cPJykpibCwMAzDAGDo0KFtZgpYrVYcDof7+OoMBBHpHHp1ifgom83GihUriIuLw2KxEBcXx4oVK7TtkIiIiHhNZmYmtbW17uOIiAjmzZvHK6+8wsiRI4Gm2Y/Hjx8HoKKigujoaI/nGDRokPv6qVOn6Nevn5eiF/FPKlwo4sNsNhs2m42ysjKGDRvW1eGIiIiIn2ldI2nChAmEhYVxyy23kJ+fD0BqaipFRUXs3buX0NBQ7r33XgAKCwtJSUlh2LBhfPDBB+Tk5AAwd+5cr45BxN8oSSAiIiIiIp0iNjaWiooK93FpaSmlpaXExcWRl5fnPr9gwYI2fdPS0tyPZ8+e3bmBioiblhuIiIiIiEinUI0kkeuPkgQiIiIiItIpVCNJ5Pqj5QYiIiIiItJpVCNJ5PqimQQiIiIiIiIiAihJICIiIiIiIiLNlCQQEREREREREUBJAhERERERERFppiSBiIiIiIiIiADa3UBERERERLzE6XSyfv16qquraWhoYOLEifTq1YuNGzdisVgICgoiNTWVHj16uPu4XC6Ki4s5d+4cgYGBzJkzh6ioqC4chYhvU5JARERERES84uDBg4SFhZGWlsaVK1dYvnw5kZGRzJgxg/79+7N371527drF9OnT3X2OHj1KQ0MDS5Ys4dSpU2zevJkHH3ywC0ch4tuUJBAREREREa9ITEzk1ltvBZpmCAQEBHDffffRs2dPABobGwkK8vwXpbKykoSEBABiYmI4c+aMd4MW8TOqSSAiIiIiIp2moKCA+Ph4EhMTGTp0KGvXrsVut7NmzRpSUlLcCYKqqirefvttxo4d69HfbrdjtVrdxxaLhcbGRq+OQcSfaCaBiIiIiIh0ioKCAjIyMqitrQWaEgHFxcW8//779OrVi5CQEADee+89SkpKGDt2LBERER7PERISwu7du9mxYweBgYE4nU4CAvRZp0hn0atLREREREQ6RWZmpjtBADB69GhiY2PZuHEjGRkZlJSU8Pbbb1NcXExISAjh4eFtniMwMJDq6mqWLFnC8OHDvRm+iF9SkkBERERERDpFZWWlx3GfPn1wOp3ccsstrF69mpqaGl5//XV3cmD37t1s3boVgMLCQi5duoTT6aR3797k5OSwf/9+XC6X18ch4k+03EBERERERDpFbGwsFRUV7uPi4mKKi4sZPHgwkydPZu7cuSQlJQGwbds2evTowR133AFAWloaAA6Hg7vuuoshQ4YAsGzZMhobG7XkQKSTKEkgIiIiIiKdYubMmWRnZ7uPAwICmDdvHrfccgvV1dWEhIRw8eJF1q1bx6VLl+jduzfJyclYLBZ3n+DgYLZv387OnTsJCQlRgkCkk+nVJeJnTp06RX5+frvX6uvryc3N5cKFC94NSkRERHxSSUmJx/Ho0aO5+eab2bx5s7smwaZNm0hJSWHkyJEAHD161KOP3W6noaGB9PR0YmJiCAwM9Fr8Iv5ISQIRP7Jr1y6KiopoaGhoc+3MmTPk5eVx8eLFLohMREREfNEXqUlw5swZ4uLiAIiOjuaDDz4APqtJUFdXR2RkJDk5ORw7dkyzCEQ6mV5hIn4kMjKS+fPnt3utoaGBBx54gD59+ng5KhEREfFVsbGxHsfFxcU888wz/PWvfyUwMJC5c+cCYLFYmDx5MomJidjtdqCpJkGvXr1wOBykpKSwZMkSli5d2u6HHSLScVSTQMSP3HrrrVRXV7d7rfWbuIhId2IYRjCQC8QDVuCXwBEgH3AB7wHfN02zsYtCFJF2tK5JAHDDDTfw4IMPMnz4cJKSknj11Vfd1+x2O6GhoR7trVYrDofjmtdFpGNpJoGIDysoKCA+Pp7ExETi4+MpKCjgww8/5Pz5823amqbJc889x9mzZzl8+HAXRCsi8rkeBj4yTXMC8C3gD8B/Aj9rPmcB5nZhfCLSjtY1CSIiIliwYAGvv/66uwbBgAEDKC8vB+DEiRNtPrgYNGgQx48fv+Z1EelYmkkg4qMKCgrIyMigtrYWgIqKCv74xz96bEN0ldPpZNOmTTz66KP8+c9/5siRIyQnJ9OjRw9vhy0ici1rgLXNjy1AA5AMbG8+txGYBhS27lhWVuaN+L60urq6bhtbZ9PY/WfsrWsSTJgwgbCwMG655RaeffZZAEaOHElJSQmNjY307NmTm2++mbKyMrZv38748ePp2bMnb731FocPHyYgIIAxY8Zcdz9Df/u9t+bP478ex64kgYiPyszMdCcIrjp37hzr169nzpw5ABw6dAiHw0FMTAxRUVGEhYVhsVgYMGAAFRUVJCYmdkXoIiJtmKZ5GcAwjJ40JQt+BjxjmqarucmnQK/2+g4bNswrMX5ZZWVl3Ta2zqax+8/YY2NjPT6gKC0tpbS0lLi4OPLy8tzn77rrrjZ9W/6ckpKSOjfQTuZvv/fW/Hn83Xns+/bta/e8kgQiPqp15h6a/kj17t2bvn37Ap+94VZWVrrX9y1atIitW7e6iwaJiHQXhmEMommmwLOmaf7JMIzftrjcE2i/6IqIdJmsrCyPmY0AgwcP5tFHHwXgww8/ZMOGDQQEBHDjjTcyZ84cLBaLu63L5aK4uJhz584RGBjInDlziIqK8vo4RPyJahKI+KhrvYEmJCS0qUlgtVq5ePEizz33HDk5OVRVVakokIh0K4Zh9AM2A0+ZppnbfHq/YRiTmx/PAP7aFbGJyLXZbDZWrFhBXFwcFouFWbNmsWTJEm688UYAtm/fzqRJk1i8eDFOp5Njx4559D969CgNDQ0sWbKEqVOnsnnz5q4Yhohf+VpJAsMwxhiGsa2DYhGRTjZu3Di++c1v4nK5PM5HRkZy7tw57rvvPhYsWMCpU6eIjIzsoihFRNr1z0Ak8H8Nw9jWfP/xM+DfDMPYDYTwWc0CEelGbDYb5eXlHD58mN/+9rdkZGS4r/Xv358rV67gcrmw2+0EBgZ69K2srCQhIQGAmJgYzpw549XYRfzRV15uYBjG/wcsAGo6LhwR6SgXL15s99wbb7zBP/zDPwCeNQluuOEGli9fDjRtTXTx4kUGDBjg1ZhFRK7FNM0fAj9s59Ikb8ciIl9d6+2Yo6KiKCkpYceOHYSGhhIfH+/R3m63Y7Va3ccWi4XGxkYCAjQhWqSzfJ1X1/vAvR0ViIh0rPa2B4qKimLChAkEBTXlB5OSkkhOTubKlSvU1tbyf/7P/+Gpp57CbrfzySefeDtkERER8UGtt2Ret26d+1ppaSnp6en84Ac/YPjw4WzatMmjr9VqxeFwuI9dLpcSBCKd7CvPJDBN8yXDMOI/r0133erhetyGoqNo7P4z9rvuuqvNdocXL17k0qVLREVFefwsqqqqANx7FAcFBVFeXk7v3r29Fm9n8rfffUsau3+OXUSku2hvS+af/vSn/PCHTRODwsLC3DMFevbs6b4nuWrQoEEcO3aMxMRETp06Rb9+/bw7ABE/1Km7G3TXrR668zYUnU1j95+x7969u825srIyevToweDBgz1+FqGhoezbt4/4+HhCQkIoKSkhNjbWZ35e/va7b0lj755jv9aWQyIivqa9LZnr6urcyYA5c+bw0ksvERAQQGBgoHtJZGFhISkpKQwbNowPPviAnJwcAObOnevdAYj4IW2BKOKjWs8iuOrcuXPuxy1rEtx444288MILuFwu+vTpo8KFIiIi8rW1tyVzdXU12dnZ/O///i+xsbEsXry4TZu0tDT349mzZ3dqjCLiSUkCER8VGBiI0+lsc/7y5cv07dsXaKpJAOB0OrHb7SxdupSQkBBycnKIiYnxarwiIiLie2JjY9v94KK92kki0j18rSSBaZrlwNiOCUVEOlJ7CQKAxsZG9+OrMwmSk5OZNm2aeybBiBEjuOGGG7wVqoiIiPiorKwsj5oEAOHh4WRlZXVhVCLyeTSTQMRHxcXFtZu579WrF0uXLgU+m0kAYBgGhmF4LT4RERHxfTabDWiqTVBZWUlsbCxZWVnu8yLS/Wj/EBEflZWVRXh4uMc5Ze5FRETE22w2G+Xl5Rw+fJjy8nIlCES6OSUJRHyUzWZjxYoVxMXFYbFYiIuLY8WKFXpjFhERERGRa9JyAxEfZrPZsNls3XorOBEREfEvp06d4rXXXmPRokWcPXuW1atXExUVBcAdd9zBbbfd5m5bX19PYWEhNTU1hISEkJqaSkRERFeFLuIXlCQQERERERGv2LVrFwcPHiQ4OBiAs2fPMnbsWL75zW+2237v3r307duXyZMn895777Fjxw5mzJjhzZBF/I6WG4iIiIiIiFdERkYyf/589/GZM2c4fvw4eXl5vPLKK9jtdo/2lZWVJCQkAJCQkMDJkye9Gq+IP1KSQERE/h979x4eZX3n//85M5lMEmIg53DITMppxJQaySpEW5UUbCUoWlcODtaAkqrdQ/Va1/bK7rXf314713fda3u57kHaYEIszCrtWmhBDqJRqXwpSEREhOGYxACJOYAhp5nMZH5/ZDNlQvAEmcGZ1+Ofzv2573v6/pArzuR9fz7vt4iIyIhxuVzk5eWRn5/PvHnz2LhxY/Dc+PHjmTt3LsuWLSM1NZW333475F6Px4PFYgHAYrHQ29sb1thFYpGSBCIiIiIiMiJcLhdlZWXU19cTCASor6/nZz/7Ga2trQBMmzaNcePGBV83NTWF3G+xWPB6vcBAwiAhISG8ExCJQUoSiIiIiIjIiCgvL6e7uztkrLe3l48//hiAtWvXcurUKQBOnDjB2LFjQ67Nzc3l6NGjABw7dgyr1RqGqEVim5IEIiIiIiIyIhoaGoYdH1wdUFJSwrZt26iurubjjz/m1ltvBWDNmjX4/X5uvPFGWlpaqKqqora2lttvvz1coYvELHU3EIkR/f39rFy5ko6ODgwGAwsXLmTixIkAfPjhh2zatCl4rcfjYfbs2cEPahEREZGvwmq1Ul9fHzJ27tw5tm/fDsDYsWNZvnz5Rfc9+OCDAJhMJu6///6RD1REgrSSQCRGvPHGG/j9fn72s59xxx13sH79+uC5b37zm/z0pz/lpz/9KTfccAOjR49WgkBEREQum9PpJCkpKWQsKSkJp9MZoYhE5PMoSSASI06cOMGUKVMAmDFjBl1dXRdd09nZybvvvsvSpUvDHZ6IiIhEIYfDQUVFJZrGfQAAIABJREFUBTabDYPBgM1mo6KiAofDEenQROQSlCQQiWIXthxyu93Bwj+DfD5fyPGrr77K+PHjycjICGeYIiIiEsUcDgd1dXUcPHiQuro6JQhErnKqSSASpVwuF8uWLaOvrw+Arq4uDh8+zD//8z+Tk5MDQFzcwH8Cmpqa2Lp1Kw0NDWRlZfFP//RPLF68mMmTJ0csfhERERERCT+tJBCJUn/9138dTBAAdHR0MGbMGP71X/+V3NxcjMY//frn5ORw7733YjKZ+M53vsN1112nBIGIiIiMiMbGRqqrq4GBBxWrV6+murqatWvX0tnZGXJtIBBg06ZNVFZWUl1dTXt7ewQiFoktShKIRKm2traQ47Nnz9Lb20tZWRl79uzBbDbz0ksvUVNTA8DJkyexWCy89dZbfP/7349EyCIiIhLldu7cycaNG4NbHrdu3cqdd95JaWkp1157LTt37gy5/vDhw/h8Ph5++GHmzJnDa6+9FomwRWKKthuIxAiLxcLGjRs5duwYgUCAZ599lkWLFgVXFBQUFODxeOju7r6oCrGIiIjIlZCamsrChQuDXZbuu+8+rrnmGmCgXfPgVshBDQ0NwdWNEyZM4PTp0+ENWCQGaSWBSJRKTk4OOfZ4PFgsluB4IBAI2XIAcODAAWbMmBG2GEVERCT6XVhIed68eWzcuDF4bjBB8PHHH/Puu+8ya9askHsHv78MMhgM9Pf3hydwkRilJIFIlLrwAxUGMvFTpkzBYrHQ2NhIdnZ2yPne3l58Ph+jR48OZ5giIiISxVwuF2VlZdTX1xMIBKivr+dnP/sZra2twWs+/PBDNm3axAMPPMCoUaNC7rdYLHi93uDxcA85ROTK0m+YSJQaWthncE/fPffcw7Zt2/je977Hrl27cLvdwEANgzFjxkQiVBEREYlS5eXldHd3h4z19vby8ccfA/DBBx/w7rvvUlpaSmpq6kX35+bmBls4D/eQQ0SuPNUkEIlSVquV+vr64PFgdWCbzcYLL7wAQEZGRvD8+PHjWbx4cdjjFBERkejV0NAw7LjX66W/v58tW7YwevRo1q1bB4DNZmP27NmsX7+e4uJipk2bxokTJ6isrARgwYIFYYtdJFYpSSASpZxOJ2VlZcHsvcFg4Mc//jGZmZn88z//MwsXLmTixInB699+++1gReExY8bw6KOPajmfiIiIXJahDy0Azp07x/bt2zEajTz99NPD3nfvvfcGX8+fP39EYxSRUPoLQCRKORwOKioqsNlsGAwGfvCDH5CZmcn48eMZNWoUr7zySvDajo4OduzYQWpqKllZWXg8npC9giIiIiJfhdPpvKhr0qRJk3jssceAge2RVVVVrF69mk2bNhEIBEKu7evr49e//jWrV6/G5XLR1dUVtthFYpWSBCJRzOFwUFdXx8GDB/nOd75DWloaDz/8MPfee2/I/sDa2lqAYHIgOTn5osJBIiIiIl/W0IcWJSUlPPzww6SnpwOwbds2iouLWbZsGTBQQ+lCe/fuJSsri2XLlnH99dezY8eOsM9BJNYoSSASxR5//HHi4uK47rrrOHPmDM3NzVRWVvL6668D4PP5ADhz5gz9/f309vbi9/s5c+YMZ86ciWToIiIiEiUufGjxL//yL5SVlQXPnTlzBpvNBsDkyZM5ceJEyL0NDQ1Mnjw5eP7kyZPhC1wkRilJIBKlHn/8cVauXInf7wcGahJ0dnZSW1vLnDlzAII1Bwb/d/ny5Tz11FMYDAb27dsXmcBFREQkqrhcLvLy8sjPz2fevHls3LgxeC4QCGAwGICBdocejyfkXo/HE2zrbLFY6O3tDV/gIjFKhQtFotQvf/nLkOO+vj4SEhL493//dx555BHgT8mBlJQUAGpqaujq6iIQCDB69OjwBiwiIiJRx+VyhRRSbmxs5PXXX2fq1KmsWbMmpAaBx+Ph/PnzVFRUYDQaufXWW7FYLHi93uD5hISEiMxDJJZoJYFIlOrv7w85bmlpwWAw8PTTT7NlyxYMBgMvvfQSNTU1ZGZmAnDs2DGampoAyMvLC3fIIiIiEmXKy8tD6iAVFhbS29tLc3Mzd955J4FAgLq6OgAOHTpEe3s7y5cvZ+nSpbzxxhuMHz+eo0ePAgPfU6xWaySmIRJTtJJAJEY0NzcTCASIj4+nqKiI9vZ28vLySEtLw2QykZOTE1zuZzKZ6Ovri3DEIiIi8nXX0NAQcpyZmUldXR2pqalkZGRgNBp566238Pv9mM1mJk+eTFxcHC+99BKpqank5uayZ88eqqqqMJlM3HfffRGaiUjsUJJAJEY0NDSQmJjIhg0b+D//5//w9ttvU1RUBEBXVxe9vb2sWLGChIQEqqqqgqsLRERERL4qq9VKfX198LipqYnx48ezfft2Ghsb6erq4oknnsBoNPLBBx/Q3NwMwIMPPsj69evx+/3cf//9kQpfJCYpSSASIw4fPszs2bP52c9+xpo1a7j//vvZtWsXaWlp2O120tPTefbZZzEajSQlJQXrFIiIiIh8VfPmzWPlypXB4/fff5+ioiIKCgr49a9/TWZmZrBGksVi4ZNPPmHVqlUYjcZgPSURCS8lCUSilM1mC8ncX3vttZw+fZpXX32Vd955h3feeYfFixcHz3u9Xp544gmSkpIiEa6IiIhEoc2bN4ccz5w5k66uLjZu3Mivf/1rdu7cGTyXk5PDiRMn+MlPfoLRaOTf/u3f9L1EJAKUJBCJUk6nM6SasNVqZcyYMTz66KO8/vrrtLa2Bq8NBAKcOXOGf//3fwcgOTmZRx55RNl7ERERuSxDaxI0NDRwyy23MGfOHPbt20dOTk5wZeOYMWNIT0/n5ZdfJhAI8I1vfINTp04xZsyYCEUvEpvU3UAkSjkcDh566CFMJhMA2dnZjB07lp/+9KfMmTMHj8cT7IDg9XoZNWoUjz32GE888QTx8fF8+umnkQxfREREosDQbgQdHR10dHSQkpLCuXPn+Pa3v01RURF2ux2Px0NWVhYrVqygrKyMsWPH4vF4IhS5SOxSkkAkSrlcLl588UX8fj8ACQkJHDhwAJfLxYQJE/D7/cE9gHFxcfT19bF161ZcLhdJSUnBVogiIiIiX9W8efNCju+++24SExNJTExk9OjRVFVV0dnZCfypJkFFRQUvvPACzc3NWtUoEgFKEohEqaF9iXt7e0lNTaW8vJzGxkZMJlNwJUFTUxMGg4F77rmHxYsX09DQQHx8fKRCFxERkSgxtCZBQ0MDe/fuxeVyMW7cOBITE4PfORISEmhvb2fJkiUsWbKE48ePk5OTE4mwRWKaahKIRKkLixYCNDc3c9111/HAAw+wZs0azGYzu3fvJi0tjSlTpnDjjTfyq1/9ivb2dkaPHo3X641Q5CIiIhIthtYk+OMf/8iCBQvIz8/n4MGDzJ8/H7fbjdfrJTk5mby8vGBNgvT0dHp6eiIUuUjsUpJAJEqZTKbgVgOA/v5+/H4///Iv/8KePXuoqamhqKgIgJaWFj766COmTJkCQHd3N2PHjo1I3CIiIhI9rFZryIMLr9fLb37zG5YtW8bixYv5xje+ETz3wQcfkJ2dzdy5cwFYv369ahKIRIC2G4hEqQsTBABGo5GzZ89SWlrKvn37CAQC7Nq1C7fbTWZmJjk5Oezfv5/Ozk4mTJhAVlZWhCIXERGRaDG0JgHA7bffjtVqZfv27bz33nvB8cGaBKtWraKyspJPPvlENQlEIkBJApEoZbPZQo4tFgt+vx+LxYLJZMJoNDJz5kzsdjuffPIJXq+XJ554ItgNQURERORyDa1JkJeXx5QpUzh06BClpaV0dHQEz+Xk5HDy5EkWL17M4sWLaWlpISkpKdwhi8Q8JQlEotTQzP2oUaOIj48nEAgwZ84cent7g90N9u/fz/nz53nuuefo6OjgxIkTHDt2LBJhi4iISBQZWpNg0qRJeDwe0tPTeemll5g6dWpwZWNvby9paWm8/PLLuFwuJk6cyKlTpyIUuUjsUpJAJEoNzdwPHQ8EAsGxuXPncvPNN3P99dczYcIEJk6cyOTJk8MSp4iIiEQvq9UacpyUlEQgEGDr1q2UlJTw29/+llmzZmG32/F4PGRlZbFixQrKysoYO3asahKIRICSBCJRamjmvqurC6/Xy5w5c9i2bRuJiYns3LkTt9vNJ598woEDB5g9e3aEohUREZFoNHRlY09PD5mZmSxZsoRNmzbR1dUVbNk8WJOgoqKCF154gaamJtUkEIkAJQlEolRaWlrIscfjYf/+/WzYsIGHH34Yg8HALbfcgt1uD243ePHFFzl37hynT5/WdgMRERG5bENXNjY2NmKxWHC5XNx3330kJiaSmJgIQEJCAu3t7SxZsoQlS5Zw4sQJcnJyIhG2SExTC0SRGNHQ0IDdbqepqYnGxkays7OD5wZbDQG89dZbJCcna7uBiIiIXLahKxvPnz9Pf38/S5Ys4T//8z+ZPXs2Bw8exOv1kpycTF5eHi+//DKBQID09HR6enoiFLlI7FKSQCRKtbe3hxwfPnyY2bNnU1ZWxpo1a7j//vvZtWsXaWlp2O129uzZw/79++no6GDKlCkRilpERESiidVqpb6+Pnjc19fH9u3baWtro7a2FpfLxV/8xV9gNBr54IMPyM7ODj68WL9+vWoSiESAthuIRKmhhYKuvfZaTp8+zX//93/z4IMPsnfvXoqKirDb7XR3d7N3716WL1/OX/zFX3D8+PGQwoYiIiIiX4XT6cRsNgeP29raOHToEE6nk/T0dBITEzl//jwwUJPA6/UGr/V6vapJIBIBWkkgEqWcTidlZWXBYkBWq5UxY8bw6KOP8vrrr9Pa2hq8NikpicLCQqqqqvD5fPj9fgwGQ6RCFxERkShy4XeKG264gbFjxwIDWw88Hg/XXHMNAOPHj6empgafz4fP56OlpYWsrKyIxCwSy5QkEIlSDoeDnTt3UlFRgd/vJzs7m9zcXDIzM/F4PPT29tLf34/RaKS7u5t33nkHo9HI+fPnMZlMBAIBJQpERETkspSXl4esDti3bx82m42dO3fi9XpZsGABu3fvDm5/vOmmm1i9ejWBQIDi4mLi4vTniki4jehv3e23j+S7f3Xd3VaSkiIdRWRo7pGOInyam5s5cmQx/f0LARgz5o+0t5v4zW/mM2VKHzNmVFJcPLDjyGyGG25I5N13f8SoUU382Z+9wL33nuTcuYmRnMIVE2s/+wtp7pGOYng//3mkIxARCY+hhQv9fj+vvPIKBoOB559/HoDc3Nzg+cLCQgoLC8Mao4iEUk0CkSh18uRJ+vv7g8dGI/T3D4wPMhgGzsfFddPdnca4cXspKFhDIGBE/3kQERGRyzW0RtLnjYtI5I3oSoK33hrJd//qDh1qYNq0aZEOIyI099iZu8FQFHLs8TxGf38/S5e6KSoq4tQpA//0T7vIyMjAbrfz1ls5vP/+Ljo6vFgsFp59NsA3vhGh4K+wWPvZX0hzvzrnXlsb6QhERMJjaI0kGKiF5HQ6IxiViHwWPSoUiVJD6wmcO3eOUaNGAeDz+TAajdxyyy3Y7XZaW1s5dOgQo0aNIicnB5/PR1NTUyTCFhERkSjicDioqKjAZrNhMBiw2WxUVFTgcDgiHZqIXIIqgYhEqaEtDFtbW7HZbAD09vYSHx/Prl27SEtLw2w209bWRnZ2djC5oJZDIiIiciU4HA4cDgeHDh26ald4icifaCWBSIwwGo2cOnUKgOTk5JCVBjabjZkzZ2IwGDAajSQmJmqvoIiIiIhIDNJKApEolZ6eTltbW/DYYrGwa9cuzp49ywsvvMCzzz7LzJkzMRoHcoVz584lEAiwfft2srKySE9Pj1ToIiIiEqX8fj+///3vOXfuHD6fj1tvvRW73R4873a72bFjB0ajkYKCAnU6EIkArSQQiVILFy4MOfZ4PFgsluB4IBAIJghgoE7Bb3/7WzweDyUlJWGNVURERGLDBx98QGJiIsuWLWPp0qVs3rw5eM7v97Nt2zaWLl1KaWkp7733Hp2dnRGMViQ2KUkgEqUu/NCFgT7FU6ZMYfPmzTQ2NpKdnR08FwgEePnll8nOzuauu+4KSR6IiIiIXCn5+fnMnj0buPiBRWtrK2lpaSQmJmIymcjNzaW+vj5SoYrELP0lIBKlGhoaQo4PHz6Mz+djzpw5bNu2je9973vs2rULt9vN4cOHqaur49ixY1RXV1NdXc3HH38cochFREQkmrhcLvLy8sjPz2fq1Kn8z//8Dx6Ph9/85jcUFxcHr/N4PCGFky0WCx6PJxIhi8Q01SQQiVJWqzUk+x4IBNi0aRM2m40XXngBgIyMjOD5v/u7vwt7jCIiIhLdXC4XZWVldHd3A1BfX88zzzzD8ePHueuuu5g+fXrw2jNnznDs2DEqKyspKCi4KGkgIuGhlQQiUcrpdJKUlBQylpSUhNPpjFBEIiIiEmvKy8uDCQKA2bNns2DBAs6ePcsNN9wQHPf7/ezevZvExEQWLVpEbW0tJ0+eZMKECZEIWySmaSWBSJRyOBzAwIdzQ0MDVqsVp9MZHBcREREZaUO3P44dOxaPx0NiYiLV1dUAzJgxg7a2NtLS0rjxxht56aWX6OjoYMqUKaSkpEQgapHYpiSBSBRzOBw4HA4OHTrEtGnTIh2OiIiIxJih2x//+7//mzFjxvDAAw9QWloaHG9oaKCtrQ273Y7dbufNN99k9OjREYhYRLTdQERERERERsS8efNCjg0GA8XFxWRkZFBdXU17ezvwpyKFtbW1VFRUUFtbGzwnIuGlJIFIjBgsXFhZWRnyoXyhrq4u/uM//gOfzxeBCEVERCTaDG3JfO211xIXF0draytz5szhtddeAwaKKbe2tvLHP/6Rhx56iOTk5GBnJhEJLyUJRGLE4Aftww8/HPKhPOjYsWOsXbuWzs7OCEUoIiIi0WZoTQKr1UpdXR1er5cJEyZQX19PbW0tJpOJ6dOn093dzYsvvsiMGTPIzMykubk5QpGLxC7VJBCJEfX19XR0dFBZWYnJZKK1tTXk/LFjxwgEAvj9fo4ePaoaBiJy1bPb7UbgeeB6wAM84na7j0U2KhG50NCaBBaLhfb2drZv3w5AfHx8sMtBRkYGBQUFzJ07F4BTp07h8XjCH7RIjFOSQCSKuVyuYHeDFStWkJubG6wq3NvbS39/P0ajkc7OTj766CNGjRpFIBBg27ZtTJkyhbg4/SdCRK5q9wAJbre7yG63zwJ+DiwYetHtt4c7rC+mu9vKkE61MUNzj3QU4dPX9xpwOnjs8RzDYnHQ3V3A7bdDUVGA4uKBxc3p6RbS070Mdmv+5je9VFUlcP58+OO+0mLt5z5ULM//ap77z38+/Li2G4hEKZfLRVlZGfX19QQCARISEmhubiYhIYGSkhL8fj9G48B/Ao4dO0ZfXx8PP/wwycnJ9PT0cPr06c/5fxARibhvA1sB3G73H4E/i2w4IjJUW1toDaSGhtFMmdJOW1s7KSmNdHVlB8+dPz+e0aMbMBp9mEy9JCW10NWVFe6QRWKeHhOKRKny8nK6u7uDx0ajkb6+PsrLy3nnnXcAgisJmpubGT16NHFxcRgMBiwWC01NTVit1kiFLyLyRaQAn15w7Lfb7XFutzuk0tnKlYfCG9UX1NvbS0JCQqTDiAjNPXbmnp9/MxAIHh8+bGDSpBKWLt1LQUEBN954I8XFG0hOTmb8+PEcP55Lbu7zAEybNo1ly45GKPIrK9Z+7kPF8vyv5rlf8KdCCCUJRKLUhfv/ADweD36/nzlz5rBhwwYAnnvuOaZOnXrRtoL+/n527drFwYMHyczMpKSkBIPBELbYRUS+oA7gmguOjUMTBMBVW2Pl0KFDV21sI01zj525D61JMNhtyWaz8cILL1x0fbT+28Taz32oWJ7/1Tz32traYce13UAkSg1uJRh07tw5vF4vL774Il6vF5PJxF/91V9x+vRpRo8eTUdHBz6fj0cffZTu7m5mzZrFsmXLgIHOCCIiV6GdwDyA/61JcCCy4YjIUE6nk6QhG7KTkpJwDhYeEJGrjpIEIlGqv78/5Pj9998nOTmZRx55hN7eXsaPH8+ePXtITk7GbDYTFxdHVVUV1dXVAMyYMQOAyZMnc+LEiXCHLyLyRawHeu12+/8DngWeiHA8IjKEw+GgoqICm82GwWDAZrNRUVGBw+GIdGgicglfebuB2g6JfL0cPnyYSZMmkZubS1xcHHfddRdHjx7FbDZjMBi47bbbeO+99zAajVgsFsxmMzDQqkjth0TkauR2u/uBRyMdh4h8NofDgcPhuKqXXYvIn1zOSoJg2yHgpwy0HRKRq8SoUaNCjmfPnk1GRgYpKSmMHz+ejIwMioqKSE5OJiEhgcLCQlasWEFZWVkwQQADtQyu1mIrIiIiIiJyZV1O4cKQtkN2u/2itkOHDl291YSv1thGmuYeO3MfWoywpqYGgNTUVMrLy3n//feJi4vjyJEjZGZmhvzbJCcn8/bbb5OVlcXevXvJysr6Wv/bxdrP/kKae2zOXUTk6+Cjjz5i586dAEyfPp1Zs2aFnO/u7uaVV17B5/NxzTXXsGDBgpAHGSIyMi4nSfC5bYeu1uVEsbzUSXOPnbl3dHQMO37u3Dnmz5/Pjh07CAQCzJo1i8LCQlpaWtizZw8lJSVkZWWxceNGjh07RkZGBnPnzr2oEOLXSaz97C+kuV+dc79UNWERkVjR39/PG2+8wYoVK4iPj+f555/nW9/6VkiRw7fffpvp06dTUFDAO++8w969eykqKopg1CKx4XKSBF+o7ZCIRMbQlkMXjtvtdux2e8j4YKtDgPT0dEpLS8MRpoiIiMQgo9HIj3/8Y4xGI11dXfT392MymUKuaWho4Dvf+Q4wUEi5pqZGSQKRMLicR4NqOyRyFfuslkNut5tVq1ZRWVn5mU80t27dyt69e0c6VBEREYliLpeLvLw88vPzycvLw+VyAQOJgkOHDvGLX/yCvLy8i7YSeDweLBYLMFBIube3N+yxi8Siy1lJsB6Y+79thwzAsisTkohcCYOthcrLy2loaMBqteJ0Olm8eDH/9V//FVzeV1VVhd1uJzk5OXhvV1cXGzZsoK2tjYyMjEhNQURERL7mXC4XZWVldHd3AzBp0iRqampobGzkqaeeYtq0aRw9epTGxkb279/PDTfcELzXbDbjcrkIBAKYzeZgwkBERtZXThKo7ZDI1W+4lkPNzc2kpaWRmJgIQG5uLvX19eTn5wfv83q93HbbbRw7pq6mIiIi8tWVl5cHEwTwp0LKkydPJjs7m2nTptHS0oLJZMJgMFx0f1paGnfffTdr164d9ryIXHlf30pkIvK5hlveN7SlocViwePxhNyXmprKhAkTwh2uiIiIRJmGhoZhx48fP8748ePZsWNHMInwrW99i56eHtatWwdAIBDg7NmzVFVV4fP56O/vD1vcIrHscrYbiMhV7FLL+06cOMHEiROD1w1NGoiIiIhcKZcqpGy322lubuYnP/kJBw8epLW1FaPRSGJiIosWLQLA5/PxwAMPYDabOXv2LOvXrw93+CIxSUkCkSh1qeV9eXl5PProozidTgwGA3Fxcdx8880h93744Yds2rQJn8+H0WgkNzeX7OzssMYvIiIiX3/z5s1j5cqVwePi4mKsVitWq5Wuri5cLhednZ309fWRkZFBQUFB8FqLxYLX68VsNuuhhkgYKUkgEqUutbzv1KlTeDweMjMzMRgMtLa20tPTg8fjYc+ePZSUlLBp0ybmz59Pa2srR48eZcOGDfzoRz8K8wxERETk627z5s0hx4MPLWw2G3V1dQC8//77tLa2hiQIYKBu0tGjRykoKODYsWNYrdawxCwS61STQCRKXeqDtKioiISEBB577DEeffRRMjMzef/998nMzKSkpASAhx56iG9+85vcfvvtjBkzhrg45RNFRETky7vUQ4tLjV9Yk+DWW2/lww8/pKqqisbGRm666aYRi1NE/kTf/EWilNPpZPny5Xi93uBYfHw8CxcupKuri1WrVmE0GvF6vSHbEgAMBgOrV6/m/PnznD17ltLS0jBHLyIiItHgUjUJLnyYceEKggtrEiQnJ7N06dKRD1JEQmglgUgU8/l8wdfLly/nySefpLW1ld7eXpYuXUppaSkdHR2YzeaQ+7Zu3UpKSgodHR3MmjWLw4cPhzt0ERERiQJOp5OkpKSQsaSkJJxOZ4QiEpHPo5UEIlHqr//6r0NaBVVVVQFw7bXXsnjxYqqrq4mLi8Pn8zFmzJiQe+Pj4zl48CDjxo3j2LFjId0QRERERL4oh8MBDBRUbmhowGq14nQ6g+MicvXRSgKRKNXW1jbseE9PD0ajkfb2dpqbm4mLi8NkMuF2u3n++efx+XwcPXoUo9HIJ598QmtrKx999FGYoxcREZFo4XA4qKur4+DBg9TV1SlBIHKV00oCkRgx2HIoJyeHhIQEnnrqKQB++ctf0tHRQVFREXa7HYAnn3yS+vp6/vCHPzBt2jT8fn8kQxcRERERkTDRSgKRKGU0hv5619TUUF1dzbp16/D5fPT09OD3++ns7CQ5OTnk2pMnT/Luu+8yd+5cDh48yKxZs8IZuoiIiIiIRIhWEohEqQvrEcCfVhJkZ2eTnp7O2rVrCQQCZGRkkJqaSktLC3v27OHOO+9ky5YtWCwWfv3rX5OZmcmePXuYPXt2hGYiIiIiIiLhoiSBSJQymUwh2wRqamoAMJvN/PznP+eRRx4hPj6eyspKJkyYQEpKCiUlJQDceeed1NbW8qMf/YjExMSIxC8iIiIiIuGnJIFIlLpUHYG+vj7y8/N59tlnAbDb7aSkpISsJNi8eTP9/f0899xzxMXFMWPGDIqLi8MZvoiIiIiIRICSBCJRymazUV9ff9F4Xl4eH374IU888QTx8fFUVVXR2dlJZmZmcCVBXl4eRUVF2GwFUy5aAAAgAElEQVQ2NmzYwNixY8MdvoiIiIiIRICSBCJRyul0UlZWRnd3d3AsKSmJv//7v6evr4+1a9diNBqxWCzU19eTn58fvG727Nm8+uqrBAIBPv30U6ZPnx6JKYiIiIiISJipu4FIlHI4HDz00EOYTCZgoEbBQw89RHFxMe3t7SxdupTS0lJaWlro6OgIuffNN99k5syZdHd34/P5OH/+fCSmICIiIiIiYaYkgUiUcrlcvPjii8HaBLfddhsej4df/epXxMXFkZiYiMlkIjk5+aIkwcKFC8nPz+fxxx8nOTmZAwcORGIKIiIiIiISZtpuIBKlysvLQ7YaDHY3uOmmm7jnnnvo6ekhPj6ezs5OkpOTQ+5dt24ds2bNYtOmTfT395OUlBTW2EVEREREJDKUJBCJUkOLFhYXF2O1WsnOziY9PZ21a9cSCATIyMggNTU12N2gpKSEb3/722zfvp2UlBS6u7vp7++P0CxERERERCSclCQQiVImkymkDeLgSgKz2czPf/5zHnnkEeLj46msrGTChAmkpKQEuxu88847LFiwgPT0dD788EOOHz8ekTmIiIiIiEh4KUkgEqUuTBBcqK+vjzvuuCO4kqCgoICUlJSLVhL87ne/w2QyYTabueuuu8IcvYiIiIiIRIKSBCJRymazXbTlYHDcbrdjt9tDxjMzM4MrCXJzc1m+fHlY4hQRERERkauHuhuIRCmn03lRwcGkpCScTmeEIhIRERERkaudkgQiUcrhcFBRUYHNZsNgMGCz2aioqMDhcOB2u1m1ahWVlZXU1tZe8j0OHDhAZWVlGKMWEREREZFI0nYDkSjmcDhwOBwcOnSIadOmAQO1CrZt28aKFSuIj4+nqqoKu91+URvEM2fOsG/fPgKBQCRCFxERERGRCFCSQCTGtLa2YrFYWLt2LUajEYvFQn19Pfn5+cFrTp48icvlIisri7a2Nj788EO++c1vRjBqEREREREJB203EIliLpeLvLw88vPzycvLw+Vy0dPTQ3t7O0uXLqW0tJSWlhY6OjqC9/T397Nt2zZmzpzJwoULyczMVIJARERERkRfXx9VVVW0traGjDc2NlJdXT3sPV9026SIfDVaSSASpVwuF2VlZXR3dwMwadIkampqOH78OImJiSQmJgKQnJwckiQ4c+YMn376KbW1tezduxefz8err74a7HwgIiIiciWcPn2aTZs2hXwPAdi5cycffPABZrP5onu+6LZJEfnqtJJAJEqVl5cHEwQANTU1VFVV8eqrr+Lz+ejp6cHv99PZ2RnywTp+/HjuuOMOfvjDH/LYY4+RnJw87Ie0iIiIyOXw+XwsWrSIjIyMkPHU1FQWLlw47D2tra2kpaWRmJiIyWQiNzd32JbPIvLVKUkgEqUaGhpCjouLiyktLWX27Nmkp6ezdu1aKisrycjIIDU1lZaWFl599VUApk2bxrhx4wBISEigqakp7PGLiIhIdBhu+yOA1Wpl9OjRF11/3XXXYTKZhn0vj8dDQkJC8NhiseDxeEYmcJEYpSSBSJRKS0sLOa6pqaG6upqqqio8Hg9Lly7l4YcfxuPxMGHCBDIzM4NbCtauXcupU6cYM2YMM2bMYOzYsZGYgoiIiHzNDW5/rK+vJxAIBLc/PvPMM/T393/p9xuaFBiaNBCRy6eaBCIxpr+/nzvuuIO1a9cSCAQoKCggJSWFlpYW9uzZQ0lJCSUlJWzZsgWj0UhycjJ33XVXpMMWERGRr6Hhtj8C2Gw2nn766S/9fhkZGbS3t9PT00N8fDwNDQ3cfPPNVyxeEVGSQCRqtbe3X3Lcbrdjt9tDxi9cSTB27FiWL18+4jGKiIhIdBu6/fHzxi/lwIEDeL1eCgsLh33YISJXjpIEIlHKarUOW8jHarVGIBoRERGJRV/k+0hpaelF58eMGcMjjzwSPJ4+fXrw9XAPO0TkylFNApEo5XQ6SUpKChlLSkrC6XRGKCIRERGJNZ/3faSvr4+qqipaW1uBgW2Rv/vd76iqqqKqqopPPvnkovd0u92sWrWKyspKamtrR34SIjFGSQKRKOVwOKioqMBms2EwGLDZbFRUVOBwOCIdmoiIiMSIz/o+cvr0aVavXh2yRfLIkSMALF++nOLi4mANg0F+v59t27axdOlSSktLee+99+js7AzrnESinZIEIlHM4XBQV1fHwYMHqaurU4JAREREwu5S30d8Ph+LFi0iIyMjeO21114bLJh87ty5izoXtLa2kpaWRmJiIiaTidzc3GG3M4jIV6ckgYiIiIiIjBiXy0VeXh75+fnk5eXhcrmAgboEo0ePvuh6o9HIhg0b2LJlS0gtAri45eHQlogicvlUuFAkBrndbnbs2IHRaKSgoIDCwsKQ811dXWzcuJGenh4CgQD33HMPaWlpEYpWREREvq5cLhdlZWXBNoiTJk2ipqaGxsZGnnrqKfx+P01NTZw9ezZkRcHcuXM5fvw4GzZs4C//8i+Jj48HBpIC7e3trFq1CqPRiNlsJjs7OyJzE4lWShKIxJjBvXwrVqwgPj6eqqoq7HY7ycnJwWu2b9/O9OnTyc/P5+TJk8GlfSIiIiJfRnl5eTBBAARrDNhsNh588EE2bdpEX19f8Pz+/fv59NNPOXPmDGazGZ/Ph8FgCJ5PTU2lubmZH//4xyQnJ/Ov//qvzJ07N3wTEokB2m4gEmO+yF6+jz/+mI6ODn71q19x4MAB8vLyIhOsiIiIfK01NDRccnywJoHZbA6OT5s2jf3799PW1kZXVxff/va3MZvNHDhwgNraWs6ePUtWVhavvPIK1dXVjBs3LqTwoYhcPiUJRKLYcHsAv8hevsFCQT/84Q8ZPXo0O3fuDHfoIiIiEgWsVuslxwdrEuTk5JCamgrARx99xPXXX8/jjz/O2LFjmThxIgDTp0+nsLAQj8dDeno6K1asoKysDJvNppoEIleYthuIRKlL7QE8ceJE8AMXLi4ABJCYmIjdbgdg6tSpF7UfEhEREfki5s2bx8qVK4PHxcXFWK1Wxo0bR39/P0Zj6DPLffv2YTAYOHHiBE1NTaxfv54lS5YEt0UOfbgx3PcYEbk8ShKIRKlL7QHMy8vjySefpKenh/j4eBoaGrj55ptD7rVarRw9epTrr7+e+vp6MjMzwxq7iIiIRIfNmzeHHF9Yk8DpdF50/bJly4Kvq6urmT9/fkjdpIyMDNrb2z/ze4yIXB4lCUSi1KX2ANbX13PHHXewdu1aAoEABQUFpKSk0NLSwp49eygpKeGOO+5g48aN7N27l4SEBH7wgx+EOXoRERGJBp9Vk+DLOHDgAF6vl8LCwmG/x4jIlaMkgUiUslqtFxUkHBy32+3B7QSDMjMzKSkpAWDMmDE8+OCDYYlTREREotdnfR8ZVFpaOuy9F45Pnz49+Hq47zEicuWocKFIlHI6nSQlJYWMJSUlDbu0T0RERGQkfN73kb6+PqqqqmhtbQ2e/8Mf/kBlZSUVFRW89957F72n2+1m1apVVFZWUltbO7ITEIlBShKIRCmHw0FFRQU2mw2DwYDNZqOiogKHwxHp0ERERCRGfNb3kdOnT7N69eqQFoZ1dXU0NjayfPlySktL6ejoCHk/v9/Ptm3bWLp0KaWlpbz33nt0dnaGe1oiUU1JApEo5nA4qKur4+DBg9TV1SlBICIiImF3qe8jPp+PRYsWkZGREbz22LFjZGVlsW7dOl566SWmTp0a8l6tra2kpaWRmJiIyWQiNzd32O0MIvLVKUkgIiIiIiIjxuVykZeXR35+Pnl5ebhcLmCgLsHo0aNDru3u7ub06dPcf//9lJSU8Nvf/pZAIBA8P7Tl4dCWiCJy+VS4UERERERERoTL5aKsrCzYlnnSpEnU1NTQ2NjIU089hd/vp6mpibNnz5KRkcH58+c5e/Ysa9aswefz0dbWRnt7O+np6cBAUuCTTz6hoqICo9HIqFGjyM7OjuQURaKOVhKIiIiIiMiIKC8vDyYIAGpqaqiqqmLlypU0NTWxevVq+vr6gudvvPFGUlNTeeihh8jIyCApKYnU1NTg+YSEBNrb21myZAlLlizhxIkT5OTkhHVOItFOKwlERERERGRENDQ0XHJ8sCbBypUrg+NTp06lvr6e559/no6ODu6//36MRiMHDhzA6/WSnJxMXl4eL7/8MoFAgPT0dHp6esI1HZGYoCSBiIiIiIiMCKvVOmxhQavVitVqBSAnJydktcDcuXNpb29n3rx5fOMb3wBg+vTpAHzwwQdkZ2czd+5cANavX6+aBCJXmJIEIiIiIiIyIubNmxeyUqC4uBir1cq4cePo7+/HaLx493Nvby9tbW3BBMGFLBYLXq83eOz1ekMKGYrI5VOSQERERERERsTmzZtDjmtqagCw2Ww4nc5h76mvrx82QQAwfvx4ampq8Pl8+Hw+WlpayMrKurJBi8Q4JQlERERERGREfFZNgktpbW0N2X4AsGvXLtLS0rDb7dx0002sXr2aQCBAcXExcXH6k0bkStJvlIiIiIiIjIjPqkkwqLS0NOTcLbfcctH1RUVFwdeFhYUUFhZeuSBFJISSBCIiIiIiMiKcTidlZWUhbRCTkpKCWw36+vpYs2YNd999NxkZGfh8Pn73u99x9uxZLBYL8+bNIz09PeQ9a2trqa2txWg0cuuttzJ16tSwzkkk2ilJIBKD3G43O3bswGg0UlBQcFE2/syZM2zatIm4uDiys7O58847MRgMEYpWREREvq4cDgcA5eXlNDQ0YLVacTqdOBwOTp8+zaZNm+jo6Ahe/9577xEfH88jjzxCa2srW7ZsYenSpcHznZ2d7NmzhxUrVuDz+Vi9ejUTJ07UlgORK+jicqIiEtX8fj/btm1j6dKllJaW8t5779HZ2RlyzcaNG/n+97/PsmXLSEhI4MCBAxGKVkRERL7uHA4HdXV1HDx4kLq6umDiwOfzsWjRIjIyMoLXtrS0MHnyZAAyMjJoaWkJea9Tp06Rm5tLXFwcCQkJpKWl0dzcHL7JiMQAJQlEYkxraytpaWkkJiZiMpnIzc29aK9gR0cHubm5AOTm5n5mcSERERGRz+JyucjLyyM/P5+8vDxcLhcwUJdg9OjRIdfm5ORw5MgRAoEAjY2NnD9/nv7+/uB5j8eDxWIJHsfHx+PxeMIzEZEYoSSBSBQb7kPZ4/GE9BO2WCwXfbimpqZSV1cHwJEjR+jr6wtn2CIiIhIlXC4XZWVl1NfXEwgEmDRpEjU1NTzzzDMhf/wPuuGGG7BYLKxevZpDhw4xduxYjMY//clisVjwer3BY6/XG/K9RkQunzbviESpwQ/lwUJBgx/KJ06cYOLEicHrhiYNABYsWMDWrVvZsWMHVqsVk8kU1thFREQkOpSXl4cULaypqQHAZrPx9NNPX3T9qVOnmDhxIt///vc5ffo0n376acj58ePHU1NTg8/nw+fz0dLSQlZW1shOQiTGKEkgEqUu9aGcl5fHk08+SU9PD/Hx8TQ0NHDzzTeH3Hv06FF+8IMfkJSUxObNm5kyZUpYYxcREZHocKkti5caT09P53/+53/4wx/+QEJCAnfffTcAu3btIi0tDbvdzk033cTq1asJBAIUFxeraKHIFabfKJEodakP3/r6eu644w5+9atf0dbWxqxZs0hJSaGlpYU9e/ZQUlLCqFGjeO655wBISUlh7ty54QxdREREooTVar2o9tHg+KDS0tLg66SkJH74wx9edH1RUVHwdWFh4UWdmUTkylGSQCRKfdaH8jXXXIPBYCA+Pp5vfetbAGRmZlJSUgIMLPW78847KSgo4J133mHv3r0hH84iIuFkt9tHA2uBFCAeeNLtdu+y2+2zgOcAH/Ca2+3+/yIYpogMw+l0hmx/hIFEgNPpjGBUIvJZVLhQJEo5nU6SkpJCxgY/lIdrOXShhoaGYPuhyZMnc/LkyRGPV0TkMzwJvOF2u28DSoH/+t/xXwAPAN8GZtrt9hsiE56IXIrD4aCiogKbzYbBYMBms1FRURFsgygiVx+tJBCJUg6Hg507d1JRUYHf78dkMvHQQw99oQ/lC9sLWSwWent7RzpcEZHP8iww2IYlDui12+0pgMXtdh8HsNvt24A5wL6hNx86dChccX4pvb29V21sI01zj625z5gxgy1bttDb2xsslhxr/wax+HO/UCzP/+s4dyUJRKKUy+XixRdfxO/3A3Dbbbfh8Xh45plneOqpp0LaCQ012F7IbDYP2/1ARGSk2O32h4Enhgwvc7vd79rt9hwGth38hIGtBx0XXHMemMgwpk2bNhKhXrZDhw5dtbGNNM1dc481sTx3iO35X81zr62tHXZcSQKRKPVlWw5dKDc3l6NHj1JQUMCxY8dCiguJiIwkt9tdCVQOHbfb7dOBl4G/cbvdb//vSoJrLrjkGuBceKIUERGJXqpJIBKlvmzLoZ6eHtatWwfArbfeyocffkhVVRWNjY3cdNNNIxaniMjnsdvt1wG/AR5wu91bANxudwfgtdvtk+x2uwH4HvCHCIYpIiISFS5rJYHdbr8XuN/tdj9wheIRkSvky7YcSkxMZNGiRQAkJyezdOnSEY9RROQL+r9AAvCc3W4H+NTtdi8AHgVcgImB7ga7IxeiiIhIdPjKSQK73f4cA1n7969cOCJypXxey6G+vj7WrFnD3XfffckuB3/84x/p7Oxkzpw5YYlZRGQ4/5sQGG78j8CsMIcjIiIS1S5nJcH/AzYAP7pCsYjIFTTYxaC8vJyGhgasVitOpxOHw8Hp06fZtGkTHR0dw97b19fHxo0bOXXq1FVbaEVERES+3g4cOMDu3bsxGo1kZWVRUlJCIBBg48aNtLW1ATB//nyysrJC7nO73ezYsQOj0UhBQQGFhYWRCF8kan1ukuAzqgyvs9vtt3/WvVdrq4evYxuKK0Vzj625X6rlUGtrK4WFhezevZvjx4/T0tIScp/X6yU1NZWEhATa2tq+9v9usfizH6S5x+bcRUSudn19fbz55ps89thjmM1mXnnlFY4cOUIgEABg+fLl1NXVUVNTw+LFi4P3+f1+tm3bxooVK4iPj6eqqgq73U5ycnKkpiISdT43SXCpKsNfxNX6BPJqbkMx0jT32Jq7y+UadiXBoAMHDjBp0qRLbjd4//33aW1t/dr/u8Xiz36Q5n51zv1SLYdERGJFXFwcy5cvx2w2A9Df309cXByTJk1i6tSpAJw7d+6iNsytra2kpaWRmJgIDHRkqq+vJz8/P7wTEIli6m4gEqVcLhdlZWXU19cTCASYNGkSNTU1PPPMM/T390c6PBEREYlhBoMh+PR/9+7deL1eJk6cCIDRaGTDhg1s2bKF6dOnh9zn8XhCEgcWiwWPxxO+wEViwGV1NxCRq1d5eXlI0cKamhoAbDYbTz/9dKTCEhERkRhz4crGe+65h5kzZ5Kdnc2MGTPYvn07Pp/vopVfc+fO5fjx42zYsIG//Mu/JD4+HhhICrS3t7Nq1SqMRiNms5ns7OxITEskal3WSgK32/2W2+1e/PlXiki4NTQ0fKnxnp4e1q1bN5IhiYiISIwZurJx/fr1/OM//iMmk4lXX30Vu93O3/7t39LX18eRI0fYv38/O3bsYNOmTZjNZgwGAwaDIfh+qampNDc3c9999/Hggw/S2NhIampqBGcoEn20kkAkSlmtVurr64cdH1RaWhp8nZiYyKJFi0KuLSgoGLH4REREJPoNXdkI0N3dzb/9279x991309rayosvvkhLSwtpaWnccsst/PKXv8RkMtHV1cV3v/tdzGYzBw4cwOv1MmHCBLKysnjllVcIBAKMGzeO9vZ2xo4dG6EZikQfJQlEopTT6aSsrCzkgzkpKQmn0wkMVBVes2YNd99990WFCz/99FN+97vfBWsXzJ8//5LFDUVEREQu5VIrGPft2xcs4rp7927MZjO33347+/fv5/rrr+fWW2+luro6WKdgsDZBQ0MD6enp/Pmf/zkAb775pmoSiFxhShKIRKnBLgbDdTc4ffo0mzZtoqOjY9h733zzTW666SauvfZajh07xhtvvHHRKgMRERGRzzN0ZWNxcTFWqxWLxUJ/fz+vv/46bW1tLFy4EIPBwL59+zAYDJw4cYKmpibWr1/PkiVLgkUOhxYqHFrIUEQun7obiEQxh8NBXV0dBw8epK6uLpg48Pl8LFq06JKrA+644w6mTJkC/KklkYiIiMiXNW/evJDjmpoaqqurMRqNrFmzhg8++IDu7m62bdtGIBBg2bJlIUmAlJSUYIIAICMjg9OnT/OLX/yCVatWceTIESZMmBC2+YjEAiUJRGKQ1Wpl9OjRlzyflJSEyWSitbWV7du3c9ttt4UxOhEREYkWmzdvHnb83Xffpa6ujrS0NEwmE4cOHaKmpgafzwcM1E3Kycnhu9/9LgAHDhygtraWnp4ezGYzRqMRv99PX18fSUlJYZuPSCzQ40GRKHaplkM//OEP8fv9NDU1cfbs2WFrErz88su0traqFoGIiIh8ZZeqSVBbW8ubb74ZXCXwm9/8hry8PJqamoJ1kwwGA729vcCfahK43W4mT57M/PnzAVi3bh3Nzc2MHz8+DLMRiQ1aSSASpS7VcshsNtPU1MTq1avp6+sb9t7f//739PT08OMf/5jvfve7vPHGG2GOXkRERKLBhV2Vho4PJgh2796N1+tl4sSJmM1mioqKWLp0KfPnz+e3v/1tsJAyDNQgsFgsweP4+HgVLhS5wpQkEIlSl2o5VF5eHqxJYDabg+d6enpYt24dAOfPn8dkMrFhwwZee+01mpubwxq7iIiIRIehNQmKi4spLS3F4XDQ39/Pa6+9xokTJ4KFC9PT0/nWt74VfJ2YmMj58+eD91ssFrxeb/DY6/WqcKHIFabtBiJR6lLL+wY7HQDk5OSQmpoKQGJiYrCDweOPPw5Aa2sr69at44EHHghDxCIiIhJthtYkqKmpAcBmszFz5kzi4uJYvHgxBoMBGGiN+Mknn1BSUsL58+fxeDxcc801wfvHjx8frF3g8/loaWkhKysrfBMSiQFKEohEqbS0NNra2oLHgy2H4uLi6O/vx2j87IVEJ0+eZPPmzdx7772qSyAiIiJfyaUeWni9Xvbt24fNZuPFF18EYObMmcyYMYMNGzZQVVWFwWBgwYIFGI1Gdu3aRVpaGna7nZtuuonVq1cTCAQoLi5WFyaRK0y/USIxYjBzn56ezqpVqz7z2pMnT7J161YcDgdjxowJR3giIiIShaxWK/X19ReNx8fH8w//8A/D3nPfffddNFZUVBR8XVhYSGFh4ZULUkRCKEkgEqXa29u/1HhPTw+///3vWbRoEdu2bcPv97NhwwZgILFw1113jVisIiIiEp2cTidlZWUhdZKSkpJwOp0cOHCA3bt3YzQaycrKoqSkhP379/P+++8D4PP5aGpq4m/+5m9C6g7U1tZSW1uL0Wjk1ltvZerUqWGfl0g0U5JAJEpdKnN/YZXh0tLS4OsLaxI8+uijIx6fiIiIRD+HwwEQbMlstVpxOp0sXLiQlStX8thjj2E2m3nllVc4cuQIBQUFFBQUAPDqq69yww03hCQIOjs72bNnDytWrMDn87F69WomTpyoLQciV5C6G4hEKafTSVJSUsjY/9/evUdHed93Hn/PSBpdYogjtODURSOD458VLKK1dsNlGycxFCfUjp0LJvbgNTFrtl6Sk9ZdN91qW5/NWe2ud7fNtnUcR9kaTJieZHMcIDh2cWKlJqWOE8DmUFvn8YWCbBxfgILBEiM0o/1DQpG4mBjmAqP36xwfz/zmeZ7z/Y6Q9NNnnuf3HEvuJUmSiiWVSrFr1y6effZZdu3aRSqVorKykttuu23kTku5XG7MH/qvvvoqb7755gmXFezZs4epU6dSWVlJTU0N9fX13oVJyjNDAqlMpVIpOjs7SSaTxGIxkskknZ2dI4m+JElSMaTTaZqampgxYwZNTU2k02lisRgXXHABAE899RT9/f1MmzZtZJ+f/vSnfPSjHz3hWJlMhurq6pHniUSCTCZT+CakccTzcqQylkqlSKVSdHd309zcXOpyJEnSOJNOp8esSTB9+nS6urp45ZVX+OQnP8mPfvQjBgYGRuYp2WyWhx56iBdffJHe3l4mTJgw5i5L1dXVvPHGG3zrW98iHo8zMDAw5nIESWfPkECSJElSQbS3t49ZtPDY3ZamTZtGLpfjiiuu4Nprr+X73/8+zz//PIODgxw+fJgrr7ySyy67jK6uLm688caR/S+66CL+6Z/+iS9/+cvE43G+9rWvnXB5paSzY0ggSZIkqSB6enpOOt7X10d/fz/79u3jwQcf5M0336S+vp4rrriCI0eOcOGFF5LJZIjHh66OfvLJJ6mvr+fCCy+kvr6e73znOwwODjJt2jT27NnjLZulPDIkkCRJklQQp7rbUiKR4O677waG1iSoqqriYx/7GG+99RYVFRVs2bKF3t5ebr75ZgDmzJkDDIUOkydP5nOf+xwAP/nJT1yTQMozQwJJkiRJBbFw4UK+8Y1vjDy/+uqraWxs5Dd+4zfI5XL8+Mc/Zt++fdx4443EYjF+9rOfMX36dObPn8/BgwdZvXo1d9xxx8idD6qrq8eEAplMxjUJpDwzJJAkSZJUEI888siY58fWJEgmk8yaNYvKyko+//nPE4vFAKipqaGiogKA2tpastksuVxuZP+Ghgb2799PX18fiUSCnp4e5s6dW6RupPHBkECSJElSQZxqTYL+/n6efvppkskkDz74IACzZs1izpw5rF+/npUrV5LNZpk3bx6JRIIdO3bQ399PW1sbCxYsYM2aNQwODtLa2srEiROL2ZJU9gwJJEmSJBXEr7MmwfEWLVp0wlhLS8vI4xACIYT8FSlpjHipC5AkSZJUnjo6Ok64RWFdXR0dHR0lqkjS6RgSSJIkSSqIVCpFZ2cnyWSSWCxGMpmks7OTVN2LsbsAABhtSURBVCpV6tIknYKXG0iSJEkqmFQqRSqVoru7m+bm5lKXI+k0PJNAkiRJkiQBhgSSJEmSJGmYIYEkSZIkSQIMCSRJkiRJ0jAXLpTGqaNHj/Ltb3+bT33qUzQ0NIx5ra+vj7/6q79i8uTJAFx++eXMnj27FGVKkiRJKiJDAmkcevXVV3n44Yd56623Tvr6L3/5S6644goWLlxY5MokSZIklZKXG0jj0MDAAIsXLz7hDIJjXn31VX75y1+yatUqvve973Ho0KEiVyhJkiSpFAwJpDKWTqdpampixowZNDU1kU6nAWhsbOS9733vKfdraGjg4x//OEuXLiWEwKOPPlqskiVJkiSVkCGBVKbS6TTLly9n9+7dDA4OMn36dLq6urjnnnvI5XLvuO8ll1xCU1MTAM3Nzbz22mtFqFiSJElSqbkmgVSm2tvb6e3tHXne1dUFQDKZ5Ctf+co77rthwwaam5uZMWMGO3fu5P3vf39Ba5UkSePPc889x+bNmwFoaWlh9uzZ5HI5NmzYwL59+wC49tprRxZSPiaKIjZt2kQ8Hqe1tZW2trai1y6VM88kkMpUT0/Puxrv6+vju9/9LgDz5s1jy5YtrFq1iq1bt/KJT3yiYHVKkqTxJ5fL8fjjj3PLLbewbNkytmzZQm9vL88//zwAt912G1dfffXIhxzHZLNZNm7cyJIlS1i6dCnbtm3j8OHDpWhBKlueSSCVqcbGRnbv3n3S8WOWLl068ri2tpbFixcD8L73vY9bb7214DVKkqTxKR6Ps2LFCuLxOG+//Ta5XI6Kigouv/xyLrvsMgAOHDhATU3NmP327t1LfX09tbW1AEydOpXdu3czY8aMovcglSvPJJDKVEdHB3V1dWPG6urq6OjoKFFFkiRpPDrVQsrxeJzu7m7uv/9+mpqaqKqqGhlft24djz76KC0tLWOOlclkxgQH1dXVZDKZ4jUjjQOGBFKZSqVSdHZ2kkwmicViJJNJOjs7SaVSpS5NkiSNE6dbSLm5uZk777yTbDbL9u3bR/a74YYb+NKXvsSGDRvo7+8fGT8+FDg+NJB09rzcQCpjqVSKVCpFd3c3zc3NpS5HkiSNM6daSPnSSy9lypQpLFmyhMrKSqqqqojFYmzfvp233nqLj3zkIyNjsVhsZP+Ghgb2799PX18fiUSCnp4e5s6dW/S+pHJmSCBJkiSpIE61YPJLL71ES0sLq1atIh6PM2XKFGbOnMnAwADr169n5cqV5HI5rrnmGqqqqtixYwf9/f20tbWxYMEC1qxZw+DgIK2trUycOLHIXUnlzZBAkiRJUkG800LKbW1tJ9y+MJFIsGjRohO2H702QQiBEEL+i5UEGBJIkiRJKpCOjg6WL18+5pKDYwspP/fcc2zevBkYCgFmz54NwDe/+U2qq6uBoTsuXX/99WOOuXXrVrZu3Uo8Hueqq64auRuCpPwwJJAkSZJUEMcWTG5vb6enp4fGxkY6Ojq46aab+PrXv87tt99OIpHgvvvuY+bMmSQSCWDsbZpHO3z4MD//+c+5/fbbGRgYYOXKlUybNo3KSv+skfLF7yZJkiRJBXOqhZRXrFhBPB7n7bffJpfLUVFRwWuvvcbRo0f59re/TS6XY968efzmb/7myD579uxh6tSpVFZWUllZSX19Pa+//joXX3xxKVqTypIhgSRJkqSii8fjdHd388gjj/CBD3yAqqoqqqqqmDNnDldeeSX79+8nnU7zxS9+kXh86M7tmUxm5FIEGFrDYPQtESWdvXipC5AkSZJUvtLpNE1NTcyYMYPPfOYz3HPPPaxatYpcLkdzczN33nkn2WyW7du3M2nSJGbOnEksFmPSpEnU1tZy6NChkWNVV1fT398/8ry/v5+amppStCWVLUMCSZIkSQWRTqdZvnw5u3fvZnBwkLVr1/LVr36ViooKVq9ezcDAALFYjKqqKmKxGE8//TSPPfYYAIcOHSKTyTBhwoSR41188cX09PQwMDDAkSNHePPNN5k8eXKp2pPKkpcbSJIkSSqI9vb2MXc2AOjt7eVP/uRPeOihh1i1ahXxeJwpU6Ywc+ZMBgcHWbduHQ888ACxWIzrr7+eeDzOk08+SX19PSEEPvzhD7Ny5UoGBwe5+uqrXbRQyjO/oyRJkiQVRE9PzynH29raaGtrO+G1z372syeMzZkzZ+TxqfaTlB9ebiBJkiSpIBobG9/VuKTSMySQJEmSVBAdHR3U1dWNGaurq6Ojo6NEFUk6HUMCSZIkSQWRSqXo7OwkmUwSi8VIJpN0dnaSSqVKXZqkU3BNAkmSJEkFk0qlSKVSdHd309zcXOpyJJ2GZxJIkiRJkiTAMwkkSZIklcBzzz3H5s2bAWhpaWH27Nlks1nWrVvHgQMHiMfjXHfddTQ0NIzZL4oiNm3aRDwep7W11TsdSHnmmQSSJEmSiiqXy/H4449zyy23sGzZMrZs2UJvby8vvPACuVyOZcuWcdVVV9HV1TVmv2w2y8aNG1myZAlLly5l27ZtHD58uERdSOXJkECSJElSUcXjcVasWEFNTQ19fX3kcjkqKiqYNGkSuVyOwcFBMpkM8fjYP1f27t1LfX09tbW1VFRUMHXqVHbv3l2iLqTyZEggSZIkqWDS6TRNTU3MmDGDpqYm0uk0MBQUdHd3c//999PU1ERVVRWJRIIDBw5w7733smHDBmbNmjXmWJlMhpqampHn1dXVZDKZovYjlTvXJJAkSZJUEOl0muXLl9Pb2wvA9OnT6erq4pVXXuGuu+6iubmZyy+/nHXr1rF9+3beeOMNpk+fzvz58zl48CCrV6/mjjvuoLJy6M+W40OB40MDSWfPkECSJElSQbS3t48EBMDIGgOXXnopU6ZMYcmSJVRWVlJVVUUsFqOmpoaKigoAamtryWaz5HK5kf0bGhrYv38/fX19JBIJenp6mDt3bnGbksqcIYEkSZKkgujp6Tnp+EsvvURLSwurVq0iHo8zZcoUZs6cycDAAOvXr2flypVks1nmzZtHIpFgx44d9Pf309bWxoIFC1izZg2Dg4O0trYyceLEIncllTdDAkmSJEkF0djYeNKFBRsbG2lrazvh9oWJRIJFixadsH1LS8vI4xACIYT8FysJcOFCSZIkSQXS0dFBXV3dmLG6ujo6OjpKVJGk0zEkkCRJklQQqVSKzs5OkskksViMZDJJZ2cnqVSq1KVJOgUvN5AkSZJUMKlUilQqRXd3N83NzaUuR9JpGBJIkqTzQgjhcuApYEoURUdCCLOBvwAGgMeiKPovJS1QkqQy4OUGkiTpnBdCmAj8GZAZNXw/cDPwW8CsEMK/LEVtkiSVE0MCSZJ0TgshxIBO4I+B3uGxiUB1FEUvRVE0CGwE5peuSkmSyoOXG0iSpHNGCGEZ8PvHDe8GvhNF0fZRtz2bCLw1aptDwLSTHbO7uzvfZebFkSNHztnaCs3e7X28Gc+9w/ju/3zs3ZBAkiSdM6Io+mvgr0ePhRBeBJYNBwgXAY8B1wITRm02AThwsmOeqwuljedF3Ozd3seb8dw7jO/+z+Xet27detJxQwJJknROi6Lo0mOPQwi7gAXDCxf2hxCmAzuBawAXLpQk6SwZEkiSpPPV7wJpoIKhuxs8VeJ6JEk6751RSBBCeC+whqHrARPAnVEUPZnPwiRJko4XRVHTqMc/A2aXrhpJksrPmd7d4E7g8SiKPgosBb6et4okSZIkSVJJnOnlBl/jV/cprgSOnGyjc3UVx/Nxhcl8sXd7H4/Gc//2Pj57lyRJOlOnDQlOcSuiL0RR9IsQwkUMXXbweyfb91xdxfFcXmGy0Ozd3sej8dy/vZ+bvZ9qNWFJkqRSO21IcLJbEQGEEFqA7wD/MYqiJwpQmyRJkiRJKqIzXbjwg8D3gMVRFG3Pb0mSJEmSJKkUznRNgv8O1AB/EUIAOBhF0fV5q0qSJEnSuLBhwwZqa2uZP3/+yNjbb79NZ2cnt9xyCw0NDWO2j6KITZs2EY/HaW1tpa2trdglS2XtjEICAwFJkiRJZ2vLli288cYbJJPJkbFsNsvDDz9MZeWJf6pks1k2btzI7bffTiKR4IEHHiCEwAUXXFDMsqWydqa3QJQkSZKkM/byyy+zZ8+eE84EeOyxx2hra2PChAkn7LN3717q6+upra2loqKCqVOnsnv37mKVLI0LhgSSJEmSCiadTtPU1MSMGTNoamoinU5z6NAhnnjiCRYuXDhm22eeeYb3vOc9XHrppSc9ViaToaamZuR5dXU1mUzmpNtKOjNnuiaBJEmSJL2jdDrN8uXL6e3tBWD69Ol0dXWxc+dOJk+eTDqd5vDhwxw9epSGhgaefvppYrEYO3fu5LXXXmPt2rXcdNNNI5cTHB8KHB8aSDp7hgSSJEmSCqK9vX0kIADo6uoCIJlMsmvXLmDo7IG9e/fS2tpKa2vryLarVq3i2muvHbPeQENDA/v376evr49EIkFPTw9z584tTjPSOGFIIEmSJKkgenp63tX4qezYsYP+/n7a2tpYsGABa9asYXBwkNbWViZOnJiPUiUNMySQJEmSVBCNjY0nXViwsbFx5PHoswdGW7p06cjjlpaWkcchBIZvwy6pAFy4UJIkSVJBdHR0UFdXN2asrq6Ojo6OElUk6XQMCSRJkiQVRCqVorOzk2QySSwWI5lM0tnZSSqVKnVpkk7Byw0kSZIkFUwqlSKVStHd3U1zc3Opy5F0Gp5JIEmSJEmSAEMCSZIkSZI0zJBAkiRJkiQBhgSSJEmSJGmYIYEkSZIkSQK8u4E0Lu3YsYOnnnqKeDzO5MmT+Z3f+R1isdjI64cOHWLt2rVks1lqa2v59Kc/TXV1dQkrliRJ5WrDhg3U1tYyf/58stks69at48CBA8Tjca677joaGhrGbB9FEZs2bSIej9Pa2kpbW1uJKpfKk2cSSOPM0aNH+clPfsKtt97KbbfdRiaT4fnnnx+zzebNm/nQhz7EF77wBS666CK2bdtWomolSVI527JlC2+88cbI8xdeeIFcLseyZcu46qqr6OrqGrN9Nptl48aNLFmyhKVLl7Jt2zYOHz5c7LKlsmZIII0zlZWV3HbbbVRVVQGQy+WorBx7UtE111zDzJkzGRwc5ODBg9TU1JSiVEmSVMZefvll9uzZM+ZMgEmTJpHL5RgcHCSTyRCPj/1zZe/evdTX11NbW0tFRQVTp05l9+7dxS5dKmuGBFIZS6fTNDU1MWPGDJqamkin08RiMS644AIAnnrqKfr7+5k2bdqY/WKxGLlcjvvuu49du3ZxySWXlKJ8SZJUpg4dOsQTTzzBwoULx4wnEgkOHDjAvffey4YNG5g1a9aY1zOZzJgPL6qrq8lkMkWpWRovXJNAKlPpdJrly5fT29sLwPTp0+nq6uKVV17hrrvu4sc//jH79u3jxhtvHLMewTEVFRWsWLGCnTt3sm7dOpYuXVrkDiRJUjlIp9O0t7fT09PDDTfcMPKH/4UXXkg6nebw4cMcPXqUhoYGXn/9daZPn878+fM5ePAgq1ev5o477hg56/H4UOD40EDS2TMkkMpUe3v7SEAAjFzTl0wmaW5uprKyks9//vMnDQh++MMf8sEPfpBLLrmERCJx0m0kSZJO5/gPLdauXcvGjRvp7OwklUoB8Mwzz7B3715aW1t54oknqKioAKC2tpZsNksulxs5XkNDA/v376evr49EIkFPTw9z584tfmNSGTMkkMpUT0/PScf7+/t5+umnSSaTPPjggwDMmjWLpqYmfvCDH7B48WJmzZrFww8/zKZNm4jFYiecCihJkvTrOP5DC4De3l7a29tHQoLR5syZw/r161m5ciXZbJZ58+aRSCTYsWMH/f39tLW1sWDBAtasWcPg4CCtra1MnDixWO1I44IhgVSmGhsbT7qQTyKR4O677z7pPosXLwaGUnovL5AkSWfrVB9ajB5vbW0deZxIJFi0aNEJ27e0tIw8DiEQQshjlZJGc+FCqUx1dHRQV1c3Zqyuro6Ojo4SVSRJksabxsbGdzUuqfQMCaQylUql6OzsJJlMEovFSCaTY67/kyRJKjQ/tJDOP4YEUhlLpVLs2rWLZ599ll27dhkQSJKkovJDC+n845oEkiRJkgomlUqRSqXo7u6mubm51OVIOg3PJJAkSZIkSYAhgSRJkiRJGmZIIEmSJEmSAEMCSZIkSZI0zJBAkiRJkiQBhgSSJEmSJGmYIYEkSZIkSQIMCSRJkiRJ0jBDAkmSJEmSBBgSSJIkSZKkYYYEkiRJkiQJMCSQJEmSJEnDDAkkSZIkSRJgSCBJkiRJkobFBgcHC3LgrVu3FubAkiSVgba2tlipaxgPnI9IknRqJ5uPFCwkkCRJkiRJ5xcvN5AkSZIkSYAhgSRJkiRJGmZIIEmSJEmSAKgsdQH5EEKIA/cBHwIywL+LoujFUa9/BbgJeAv4n1EUPRxCuAR4EIgBu4HlURT1jjreD4H1URTdX9Rm3qV89h5C+CRw9/D4VmBFFEXn7KIVee79D4CbgRzw36IoWlvcbs5MCGEWcE8URR87bvw64E+BAeCBKIq+FUKoBdYAk4FDwK1RFL15sm2L2cOZylPvNwG/N7ztDuA/RFGUK2IbZyQfvY/apxPYH0XRHxWr/rOVp6/9vwb+nKGfBa8BS6IoOlLENlSGnI84H8H5yMeOG3c+4nykLOcj5T4XKZczCW4AaqIomgP8EfBnx14IIbQw9MN2NrAA+GoIoQ74X8D9URR9BPg74M5Rx/uvwPuKU/pZy0vvIYQJw+PXRlE0C9gFNBSxjzORr94vBL4MzBne9v8Us4kzFUL4Q+D/AjXHjVcBX2Ool48Cy0MIU4A7gB3Dva8G/vM7bHtOy1PvtQx9r388iqJ/A7wXuLZ4XZyZfPQ+ap9/D7QUqfS8yNPXPgZ8C/hCFEW/BfwtkCxeFypjzkecjzgf+dW48xHnI2U5HxkPc5FyCQmOvbFEUfQz4F+Neq0Z+Lsoio4MJzMvADOBDwKPDm+zefgYhBA+x1B6+7fFKf2s5av3uQwll38WQvgp8ProdO8cla/e32YoxX/P8H/nfHI77CXgMycZbwZejKLon6Mo6gf+HriKUe8XQ+/B/HfY9lyXj94zwNxjn9gxdGbVOZHenkY+eieEMBeYBXyz4BXnVz76vwzYB/x+COEJoD6KoqjglWs8cD6C8xGcjxzjfMT5SLnOR8p+LlIuIcFE4OCo59kQwrFLKXYAV4UQJoQQJjH0y+c9wDPAp4a3+RTwnhDCFQylvX9anLLzIi+9M5TSfxz4CvBJ4PdCCJcVof6zka/eAV4GngO2AX9Z6MLzIYqih4CjJ3np+PflEEOp9Ojxk42NHj+n5aP3KIpyURS9DhBC+BJwAfCjghWdJ/noPYTwfoZO5f1iAUstiDz9u29g6GfCvQz9op4XQri6UDVrXHE+8ivOR4Y4H/kV5yPOR8piPjIe5iLlEhK8BUwY9TweRdEAQBRF3Qy9+X87/P+ngL3AHwCfCiH8HTA4PPZvgYuBLmApQ6d+faI4LZyxfPW+D/hFFEWvRVF0GNgEtBariTOUr94/CbwfuARoBG4IIXy4SD0UwvHvywTgwHHjJxsbPX6+eje9E0KIhxD+N/DbwGfP5Wtefw3vpvdFDP1yeoShU2NvDiEsLVqlhfFu+t/HUNLfHUXRUYZ+Toz+5E86U85HfsX5CM5HcD5yjPOR8TEfKZu5SLmEBJuBhQAhhNkMpbYMP/8XwITha3x+F5gK/CND34R/PLzYRBb4URRFfxhF0azhsVXAn0dRdK6f5peX3hlKrK8IITQMp9+zGUqyz2X56v2fgT4gM3wq4AHgwuK1kXfdwAdCCPUhhARDpzk9yaj3i6GJyE/fYdvz1bvpHYZObasBbhh1mt/56tfuPYqiv4yiqG34++B/AH8TRdGqEtScT+/ma78TuCCEcOnw+EeAZ4tcr8qT8xGcj+B85BjnI85Hxtt8pGzmImVxdwNgLfDbIYR/YGh1yC+EEO4EXgQ2AM0hhF8A/cBdURRlQwgRkA4hZBj6gqwoUe1nKy+9R1F0NITwn4CNw8f9f1EU/WPRu3l38tn7fOBnIYQcQ9cPnfOneR0vhHAzcEEURZ3D78NGhoLAB6Io2hNC+AbwYAjh7xl6T24e7v2EbUvVw5k6k95DCFcCyxj6Qd0VQgD4i+g8WUn6mDPpvYTl5t0Z/rvvDyEsA/4mDC0c9A9RFP2wZE2onDgfcT7ifMT5iPORcTYfKce5SGxw8Hw+m0WSJEmSJOVLuVxuIEmSJEmSzpIhgSRJkiRJAgwJJEmSJEnSMEMCSZIkSZIEGBJIkiRJkqRhhgSSJEmSJAkwJJAkSZIkScP+P/qJnhrgGZB+AAAAAElFTkSuQmCC\n",
+      "image/png": "iVBORw0KGgoAAAANSUhEUgAABAwAAAHeCAYAAAAfLZn1AAAABHNCSVQICAgIfAhkiAAAAAlwSFlzAAALEgAACxIB0t1+/AAAADh0RVh0U29mdHdhcmUAbWF0cGxvdGxpYiB2ZXJzaW9uMy4xLjAsIGh0dHA6Ly9tYXRwbG90bGliLm9yZy+17YcXAAAgAElEQVR4nOzde3xV1Z3//1cSEIigBlHESxLHyzJcrIpTaNVqvVFpvYztMNYztSg2zlj92a9Tp8Ok39bp9Ey1tlM7nUobq6LlWP2OVtpQb1hH22bQjvQChbDUSk4SBRU0ooaQQs7vj4Q0IQmgkpzAfj0fDx6Pc9be++T9CWq2n6y9VkEul0OSJEmSJKm7wnwHkCRJkiRJQ48NA0mSJEmS1IsNA0mSJEmS1IsNA0mSJEmS1IsNA0mSJEmS1IsNA0mSJEmS1IsNA0mSJEmS1IsNA0mSJEmS1IsNA2k3F0JoCiEcn+8ckiRJkvYsw/IdQNK7F0IYB4wHVvZz/FHg4hjjunf5+e/pekmStHsKITwEPBJjvLnz/dFABG6IMc7tHDsQaAJqgc8CBwL/GWOcnJ/UknY1ZxhIu6kQwpFAIx3/Hq8PIawPIWzbBDzrPX6Z93q9JEnaPT0EnNbt/blADXBet7HTgdoY44djjH3+8kLS7s0ZBtJuKsb4fAjh88CHYox/s+3xEMIdnS//O4QwM8bYGEI4F/gisBfQAnweWA7cARwFtANLgSuA27a9fmArkiRJQ8hDwPUhhMIYYzsdDYN/Bu4JIfxFjPEF4AzgZyGEeuAT3S8OIYwGvgOcBGwGFgJVwD7Ad4HjgFzn1/lnOu5DlgCnxhh/H0K4C9gcY7wshHAKcBNQDLQBX4wxPhxCmA38FR33L0d1HrskxviHgfmWSMnjDANp9/Y+4Hd9HYgxXtr58sOdzYKjgH8DZsYYjwcqgR8DHwfGxBiPA/6y85q/2Pb6AatAkiQNOTHG54DXgGNDCCVAAJ4CHgTO7zztDOBn/XzEV4CRQAUdzYGTgFOB/wDWA1OAE+m4l/l8jLEOuA64K4Qwp3P8syGE/YH7gGtijMcCnwYWhBAO7/w6pwJXdz4GUdv5GZJ2ERsG0u7tOOD3O3nuWcAE4OchhN8BGTo68r8DJoUQngD+Cbg5xvj8AGSVJEm7l62PJZwDLO6cabAIODuEUA7Q+T/6fTkTuC3GuCXG2BZjPDXG+ETnZ/1njDEXY9wEfK9zjBjjrcDzdMxM+ESMcSMwDXg+xvh05zkr6GgMnNb5dZbGGJs6X/8GGLuLapeEjyRIu60QQiEwmc4ZBiGEr/Dn5wp/GmP80jaXFAE/7/74QgjhMOAl4Eg6fvCeDjwWQrg6xnjfwFYgSZKGuIeAy4FWOh4pAHgcuJWOhkB/swug4zGE3NY3nfccLfT+hWUhMLzznBHAEUAzHTMMnuvj/O7XtAEbu43ngIIdlyVpZznDQNp9jer8UwgQY/xSjPG4zj9bmwVb6PwhTMcP+LNDCMcAhBBmAsuAv6NjDYNHY4xfAB6hoxGx7fWSJClZ/puO2Yyn0nF/QIyxhY7f5F/F9hsGjwGfDiEUdjYC7uv2OZ8NIRR0jlcCizuvuQn4AzAD+M8QQhkdj0GEEML76XgxCfgQ8MQurFNSP2wYSLupGOPbdEzjWxlCaOrntB8DvwohTO6cwldJx2JFvwf+lY4ZCfPpmH2wMoTwDB2LEX172+sHrhJJkjQUdT4S8GzHy/hGt0M/o2ORwSe2c/m/0DED4PfAb4EHY4w/Bv4/OrZfXN75JwLpEMLHgAuAq2KMy4FvAT+iY7bBXwPfCSEsB+4GLo0xPrur6pTUv4JcLrfjsyRJkiRJUqI4w0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPUybDC+yNKlS11ZUZKkPkydOtU9wweJ9yOSJPWtv/uRQWkYdAYYrC+10+rq6qioqMh3jLxJcv3Wbu1JY+1Ds/alS5fmO0LieD8y9CS5fmu39qSx9qFZ+/buR3aqYRBCmAbcGGM8bZvxvwT+HSgA1gJ/G2NsfddJJUmSJEnSkLDDNQxCCP8I/AAYuc14AXArcGmM8WTgYaBsIEJKkiRJkqTBtTOLHv4RuLCP8aOB9cD/CSE8CYyNMcZdGU6SJEmSJOXHDh9JiDHeH0Io7+PQOOCDwFXA88CiEMIzMcbH+/qcurq695JzQLS2tg7JXIMlyfVbu7UnjbUns3ZJkqT34r0sergeeD7GWAcQQngYOBHos2EwFBd4GMoLTwyGJNdv7daeNNY+NGt30UNJkjSU7cwjCf15ARgdQjiy8/0pwIr3HkmSJEmSJOXbO55hEEK4GBgdY6wOIcwB7u5cAPF/Yow/2+UJJUmSJEnSoNuphkGMsR6Y3vn67m7jjwPvH5BkkiRJkiQpb97LIwmSJEmSJGkPZcNAkiRJkiT1YsNAkiRJkiT1YsNAkiRJkiT1YsNAkvSuNDY2cvnll/OXf/mXnHLKKdx///35jiRJ2s00NTUxf/58ANasWcOtt97KHXfcwYMPPkgul8tvOO0WvB8ZWDYMJEnvyjXXXMNJJ53EU089xVe/+lXmzZv3jq7/xje+wS9/+UsATj/9dJYvX77Day677DJee+21d5V3V9qa4+233+byyy+ntbU135EkabdTW1tLTU0NmzdvBqCmpoaPfOQjXHrppYwcOXKnfi5I3o8M7P2IDQMpobp39LtbsmQJt9xyC/Pnz2f+/PmsW7du8MNpyFu1ahXNzc1ceumlFBUVATB27Nidvv53v/sdzz//PKeccso7+rq1tbXv6PyBsjXH3nvvzcc+9jG+/e1v5zmRJO1+SkpKmDVrVtf7DRs2cNhhhwFw2GGH0dDQkK9o2k14PzLw9yPDdvknShryamtrWbZsGcOHD+91bM2aNVxwwQUcfPDBeUim/tx1F9x++7u/vqWllOLi7Z9z2WVwySU793m/+c1vOOGEE2hvb2flypV87Wtf44orrtjpPN/5znf427/92z6PPf3003zrW9/isMMO47nnnqOtrY0vfelL/OQnPwHg05/+NNXV1UyYMIHHH3+cefPm8ac//YmRI0fyhS98gba2NtLpNMXFxbS0tPDVr36V++67jzvuuIPCwkJKSkq48cYb+73++OOP5+mnn+brX/8648ePp7GxkZEjR3LDDTdwxBFHMHfu3B45zjnnHL7xjW8wZ84cxo0bt9PfA0lKokwmQ1VVFQ0NDZSWlnL99dd3HSspKaG+vp7y8nKeffZZ/vSnP+UvqPrk/Ujy7kecYSAl0LYd/e7WrFnDr371K26//fau6VnStlatWsXkyZO55JJL+PjHP86oUaM466yzALjpppu4+OKLue666/q82duwYQNLly7lpJNO6vfzly1bxmWXXcbChQv5xCc+wX/+53/yta99DYA777yTCRMmUF9fz7e+9S2qq6tZuHAh//qv/8rVV1/Nxo0bee655/jmN7/JT3/6U5qamvjGN77BD37wA2pqajj99NOZN29ev9e3tLQAsHLlSi677DJqamq48MILue666wB65RgxYgQnnHACTz755C79HkvSniaTyVBZWUk2myWXy5HNZpk7d27XbMbzzz+fX/3qV9x1113svffejBo1Ks+JNdR5PzLw9yPOMJASYnsd/e4mTZrE+9//fkaMGMG9997Ls88+y9FHHz24YdXLJZfsfLe9L3V1DVRUVOyyPHV1dZx//vlccsklNDU18aUvfYmbbrqJT37yk7z88svcfffdzJs3j0ceeYSPfexjPa7NZrMccMAB7LXXXv1+/sEHH9yVd+LEiTzwwAO9zqmtreWVV15h9uzZXWMFBQVks1kmTJjAIYccAnT8sD/55JOZMGECQNf5mUymz+u3ToE95phjOPHEEwH4+Mc/zle+8hVef/11SkpKemUpLS1l9erVO/iuSVKyVVVVdf1P0Fatra00NjYC8Nxzz3HhhRdSXFzMgw8+yFFHHZWPmNoO70eSdz9iw0BKgK0d/a0/pLd29K+55poe5+VyOaZPn87IkSMBOOqoo1izZo0NA/WwZcsW/vjHPzJx4kQKCwspLS3lhBNOYP369fzmN7/h5JNPBuCUU07hxz/+ca8f0IWFhWzZsmW7X2PrP4PQ8UOzr5Wy29vb+cAHPsDNN9/cNbZmzRrq6+sp7jbfsaioiIKCgq73ra2tvPjii/1ef+CBB/LMM890PQu5VS6X6zXW/XuyvRsOSRL9rknQ1tYGdDx7ftdddzF8+HDKy8ttGGi7vB/p+3uyq+9HfCRBSoAddfS32rRpE/PmzaOtrY1cLsfq1atdy0C9rF69mtbWVn7xi1+wZcsW6urquO+++/irv/orNmzYwOjRowEYM2YMb7zxRq/rDzvsMF577TU2bdr0jr92UVFR12ra06dPp7a2lj/+8Y8APPnkk5x33nm9Pnfy5MksWbKEV155BYB77rmHm266aYfXr1q1ilWrVgFw7733csIJJ7DPPvv0ygEdi4gefvjh77geSUqS0tLSXmPNzc0sXrwYgBACf/d3f8ecOXM444wzBjuedjPejwzO/YgzDKQE2FFHf/ny5bS1tTF16lROP/107rzzToqKijj88MPt7quXlStXcsQRR3DjjTfyT//0T5SWlvLFL36R4447jhUrVvDWW28B8Oabb7Lvvvv2un6fffZh6tSpPPXUU5x66qnv6GufddZZXHzxxdxyyy0cffTRfOUrX+Haa68ll8sxbNgw5s2b1+u3BeXl5Vx33XVcfvnlABxwwAH827/9G+PHj+/z+q2/DRg3bhw333wzL774ImPHjuXrX/96nznKy8v57W9/Szqdfke1SFLSpNPpHjMeAYqLi/3vp94V70cG6X4kl8sN+J9nnnkmNxStXLky3xHyKsn1J632srKyHNDrT1lZWb6jDaqk/b13tytrv+GGG3Lf+973+v061113XS6Xy+XmzZuXq6mp6fO8pUuX5j7zmc/sskzb825qf+qpp3If/ehHd+rc+++/P3fDDTe846+Ry+VynT8fB+VnsX+8Hxmqklx/EmtfsGBBrqysLFdQUJArKyvLLViwIN+RBl0S/9638n7knRkK9yM+kiAlwNYtXbqzo693q66ujiOOOKLPYxUVFey///5cfPHFPPfcc5x99tl9nnfCCSdw+OGH84tf/GIgow64t956i0WLFnH11VfnO4ok7RZSqRT19fWsWLGC+vp6UqlUviNpN+X9yJ8N5P2IjyRICbD1h3H3XRLS6bQ/pPWurFq1arvPx33hC1/Yqc/Zun/wUDRt2jQWLVq0w/NGjx7N7e9lQ2pJkvSueD/yZwN5P2LDQEqIVCpFKpWirq5ul25no+R56qmn8h1BkiQlnPcjg8NHEiRJkiRJUi82DCRJkiRJUi82DCRJkiRJUi82DCRJkiRJUi82DCRJkiRJUi82DCRJkiRJUi82DCRJkiRJUi82DCRJkiRJUi/D8h1AkiRJUjI1NTXx2GOPMXv2bNauXcuiRYsoLCxk//3357zzzqOgoCDfEaVEc4aBJEmSpEFXW1tLTU0NmzdvBuDJJ5/k1FNP5bLLLmPLli08++yzeU4oyYaBJEmSpEFXUlLCrFmzut4fdNBBbNy4kVwux6ZNmygqKspjOklgw0CSJEnSIMlkMpSXlzNp0iRmzpxJTU1N17GxY8fy0EMP8d3vfpe3336b8vLy/AWVBNgwkCRJkjQIMpkMlZWVZLNZcrkc2WyWuXPnsm7dOgAefvhhLr30Uq666iqOPfZYHnnkkTwnlmTDQJIkSdKAq6qqoqWlpcdYa2srjY2NAIwaNYoRI0YAMGbMGFpbWwc9o6Se3CVBkiRJ0oBraGjoc7ytrQ2A8847j/vvv5/CwkKKioo499xzBzOepD7YMJAkSZI04EpLS8lmsz3GmpubWbx4cdfxyy67LB/RJPXDRxIkSZIkDbh0Ok1xcXGPseLiYtLpdJ4SSdoRGwaSJEmSBlwqlaK6upqysjIKCgooKyujurqaVCqV72iS+uEjCZIkSZIGRSqVIpVKUVdXR0VFRb7jSNoBZxhIkiRJkqRebBhIkiRJkqRebBhIkiRJkqReXMNAkiQNOSGEacCNMcbTQgj3AAd1HioHnooxXtTt3AKgCXiuc2hJjHHuYOaVJGlPZMNAkiQNKSGEfwQ+BbwNsLU5EEIoAf4b+D/bXHIE8JsY47mDmVOSpD3dTj2SEEKYFkJ4YjvHq0MIN+yyVJIGXFNTE/Pnz+/3eE1NDY899tjgBZKkP/sjcGEf4/8CfCfGuGab8anAISGE/w4hPBhCCAOeUJKkBNjhDINtu/x9HL8CmAI8uWujSRootbW1LFu2jOHDh/d5/JlnnuGVV16hrKxskJNJEsQY7w8hlHcfCyEcCJxB79kFAGuAr8UY/yuEcDKwAPjLvj67rq5uF6d971pbW4dkrsGS5Pqt3dqTxtp3v9p35pGErV3+H257IITwQWAa8H3gmF0bTdJAKSkpYdasWTzwwAO9jjU2NvLiiy8ydepU1q1bl4d0ktSnTwB3xxi39HHsGWAzQIzxVyGEg0MIBTHG3LYnDsV935O+H32S67d2a08aax+atS9durTfYztsGPTV5QcIIUwAvgz8FTBrR58zFLspu2uXZ1dJcv1JrH3RokV861vfYu3atRx00EFcc801FBcX9/g+bNy4kV//+tecdNJJNDY28uabb+5R36ck/r1vZe3JrH0Pcybw1X6OfRlYD3w9hPA+oLGvZoEkSXpn3suih38NjAMepGPl4uIQwqoY4/y+Th6K3ZSh3OUZDEmuP2m1ZzIZrr/+elpaWgBYs2YNN998M9dcc02P78PTTz9NYWEhS5cu5a233uJPf/oTIQSOO+64fEXfpZL2996dtQ/N2rfX0VcvAXihx0AIjwIfA24AFoQQPkrHTIPZg55OkqQ90LtuGMQY/wP4D4AQwmzgmP6aBZLyq6qqqqtZsFVrayuNjY09xqZNm8a0adMA+N3vfse6dev2mGaBpN1LjLEemN7t/aQ+zjm782Ub8NHBSSZpV2pqauKxxx5j9uzZ3Hfffbz11lsANDc3c+ihh/KJT3wizwmlZHvHDYMQwsXA6Bhj9QDkkTQAGhoa+hxva2sDYPny5bS1tTF16tTBjCVJkhJs20WYtzYHNm7cyJ133smMGTPyGU8SO9kw6N7ljzHe3cfx+bs0laRdqrS0lGw222OsubmZxYsXAzBlypRe1zizQJIkDaT+FmF+4okneP/738+YMWPylEzSVoX5DiBp4KXTaYqLi3uMFRcXk06n85RIkiQlUSaToby8nEmTJjFz5kxqamp6HH/77bdZvXq1v7iQhggbBlICpFIpqqurKSsro6CggLKyMqqrq0mlUvmOJkmSEiKTyVBZWUk2myWXy5HNZpk7d26PbZxXrlzJ5MmTKSz0f1OkocB/E6WESKVS1NfXs2LFCurr620WSJKkQbUzizC/8MILHHXUUYMdTVI/bBhIkiRJGnA7WoQZYP369ZSUlAxWJEk7YMNAkiRJ0oArLS3tNdZ9EWaAK6+8kpEjRw5mLEnbYcNAkiRJ0oBzEWZp92PDQJIkSdKAcxFmafczLN8BJEmSJCVDKpUilUpRV1dHRUVFvuNI2gFnGEiSJEmSpF5sGEiSJEmSpF5sGEiSJEmSpF5cw0BKqKamJh577DFmz57dY3zlypXU1tYCMGXKFKZPn56HdJIkSZLyzYaBlEC1tbUsW7aM4cOH9xhvb2/n5z//OZ/5zGfYa6+9uOWWWzj22GN7bYEkSZIkac/nIwlSApWUlDBr1qxe44WFhXz2s59l5MiRbNy4kfb2doqKivKQUJIkSVK+2TCQEiKTyVBeXs6kSZOYOXMmNTU1fZ5XWFhIXV0d3/ve9ygvL+81C0GSJElSMtgwkBIgk8lQWVlJNpsll8uRzWaZO3cu69at6/P8iooKrr32WrZs2cLvf//7QU4rSZIkaSiwYSAlQFVVFS0tLT3GWltbaWxs7DG2adMm5s+fz+bNmykoKGD48OEUFBQMZlRJkiRJQ4SLHkoJ0NDQ0Od4W1sbAMuXL6etrY2pU6cyZcoU5s+fT2FhIePHj+fYY48dzKiSJClBuu/a9Pbbb1NTU8PGjRvJ5XJccMEFjB07Nt8RpUSzYSAlQGlpKdlstsdYc3MzixcvBjq2T9xq6tSpTJ06dVDzSZKk5Nl216bFixczZcoUJk2axOrVq1m3bp0NAynPfCRBSoB0Ot1ra8Ti4mLS6XSeEkmSpKTbdtemxsZGNmzYwF133cXy5cspLy/PXzhJgA0DKRFSqRTV1dWUlZVRUFBAWVkZ1dXVpFKpfEeTJEkJNXHixB7bNzc3NzNy5EguueQS9t13X2pra/OYThLYMJASI5VKUV9fz4oVK6ivr7dZIEmSBl33bZ7Ly8tZuHBh17FRo0YRQgDg6KOP5qWXXspXTEmdbBhIkiRJGnA72ua5tLSU5557DoBsNssBBxyQz7iScNFDSZIkSYNgR9s8n3322dTU1PDMM88wcuRILrzwwnzElNSNDQNJkiRJA66vbZ6bm5uZN28e3/3ud9lvv/341Kc+lYdkkvrjIwmSJEmSBlxpaek7GpeUfzYMJEmSJA04t3mWdj82DCRJkiQNOLd5lnY/rmEgSZIkaVCkUilSqRR1dXVUVFTkO46kHXCGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6sWGgSRJkiRJ6mVYvgNIkiRJSqampiYee+wxZs+ezZo1a/jRj37E2LFjATjxxBOZPHlynhNKyWbDQJIkSdKgq62tZdmyZQwfPhyANWvWMH36dD74wQ/mOZmkrXaqYRBCmAbcGGM8bZvxTwKfAzYDy4ErY4ztuzqkJEmSpD1LSUkJs2bN4oEHHgDgpZdeYv369cQYGTt2LB/5yEcYMWJEnlNKybbDNQxCCP8I/AAYuc34KOCrwIdjjCcB+wIfG4iQkiRJkvYsEydOpKioqOv9IYccwllnncWll15KSUkJTz75ZB7TSYKdW/Twj8CFfYxvAj4YY2zpfD8MaN1VwSRJUnKFEKaFEJ7ofH18COHFEMITnX/+ZptzR4UQ7g8h/DKE8GAI4YC8hJa0Q5lMhvLyciZNmkR5eTkLFy7sOlZRUcHBBx/c9Xrt2rX5iimp0w4fSYgx3h9CKO9jvB14GSCEcDUwGljc3+fU1dW9+5QDpLW1dUjmGixJrt/arT1prD2Zte+uOmc3fgp4u3NoKvDvMcZv9nPJ3wPLY4zXhxAuAr4IXDPwSSW9E5lMhsrKSlpaOn7fmM1mmTt3Ltdc0/Gv64IFCzjnnHM45JBDeOGFF5gwYUI+40riPS56GEIoBL4OHA18PMaY6+/cioqK9/KlBkRdXd2QzDVYkly/tVt70lj70Kx96dKl+Y4wVG2d3fjDzvdTgRBCOB94DvhcjPHNbuefTMf9CMBDwP8drKCSdl5VVVVXs2Cr1tZWGhsbAfjoRz/KQw89RGFhIaNHj+bcc8/NR0xJ3bzXXRK+T8ejCRe42KEkSdoV+pjd+GvgBzHGpSGEKuDLwOe7Hd8HeKPz9Zt0rKvUp6E42yTps2CSXH/Sam9oaOg11tzczLx587jqqqsA+MAHPtB17IUXXhi0bIMpaX/v3Vn77lf7O24YhBAupuPxg2eAOcAvgcdDCADfjjE+sEsTSpKkpHsgxti89TXwnW2ObwDGdL4eAzTTj6E422Qoz4IZDEmuP2m1l5aWks1m+xxP0vchaX/v3Vn70Kx9ezMed6phEGOsB6Z3vr6726GdWTRRkiTpvXgkhHB1jPHXwBnAtnc2tcBMOmYinEPHLzMkDTHpdLrHGgYAxcXFpNPpPKaStD3v9ZEESZKkgfb3wHdCCH8C1gKVACGER+nY0nkecGcI4VdAG3BxvoJK6l8qlQI61jJoaGigtLSUdDrdNS5p6LFhIEmShpxtZjf+Bjipj3PO7nzZBvz1oIWT9K6lUilSqdSQnp4t6c98pECSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJEmSJPViw0CSJElSXjQ1NTF//vweY8uXL+e2227LTyBJPQzLdwBJkiRJyVNbW8uyZcsYPnx419iaNWv47W9/Sy6Xy2MySVs5w0CSJEnSoCspKWHWrFld71taWnj88ceZMWNGHlNJ6s6GgSRJkqRBkclkKC8vZ9KkScycOZOamhoA2tvb+elPf8rZZ5/NiBEj8pxS0lY2DCRJkiQNuEwmQ2VlJdlsllwuRzabZe7cuaxbt441a9bw2muv8bOf/Yz77ruPV199lYcffjjfkaXEcw0DSZIkSQOuqqqKlpaWHmOtra00NjZyyCGHcOWVVwLQ3NzMfffdx0c+8pF8xJTUjTMMJEmSJA24hoaGPsfb2toGOYmknWXDQJIkSdKAKy0t7TXW3NzM4sWLe4ztt99+XH755YMVS9J22DCQJEmSNODS6TTFxcU9xoqLi0mn03lKJGlHbBhIkiRJGnCpVIrq6mrKysooKCigrKyM6upqUqlUvqNJ6oeLHkqSJEkaFKlUilQqRV1dHRUVFfmOI2kHnGEgSZIkSZJ6sWEgSZIkSZJ6sWEgSZIkSZJ6sWEgSZIkSZJ6sWEgSZIkSZJ6sWEgSZIkSZJ6cVtFKaGampp47LHHmD17do/xGCO/+MUvKCws5LjjjmPq1Kn5CShJkiQpr2wYSAlUW1vLsmXLGD58eI/xLVu28Mgjj/CZz3yGvfbai9tvv50QAqNHj85TUkmSJEn54iMJUgKVlJQwa9asXuPr1q1j7NixjBo1iqKiIg477DCy2WweEkqSJEnKNxsGUkJkMhnKy8uZNGkSM2fOpKamptc5mzZtYuTIkV3vR4wYwaZNmwYzpiRJkqQhwoaBlACZTIbKykqy2Sy5XI5sNsvcuXNZt25dj/O2bRBs20CQJEnalZqampg/fz4Ar776Krfffju33347CxcupL29Pb/hJNkwkNfQpuIAACAASURBVJKgqqqKlpaWHmOtra00Njb2GBs3bhyvvfYaGzduZMuWLTQ0NHDooYcOZlRJkpQQtbW11NTUsHnzZgB+/vOfc8YZZ3DZZZcBHQsxS8ovFz2UEqChoaHP8ba2NgCWL19OW1sbU6dO5eyzz2bBggXkcjmOO+449tlnn8GMKkmSEmLrmkoPPPAAALNmzaKwsJAtW7bw1ltvOctRGgJsGEgJUFpa2mvxwubmZhYvXgzAlClTusZDCIQQBjWfJElKhkwmQ1VVFQ0NDZSWlnL99dd3HSssLKS5uZkf/vCHjBgxgvHjx+cvqCTARxKkREin0xQXF/cYKy4uJp1O5ymRJElKmp1ZU2m//fbj6quv5sQTT+TRRx/NY1pJYMNASoRUKkV1dTVlZWUUFBRQVlZGdXU1qVQq39EkSVJC7GhNpR/96EesX78egL322ouCgoJBzyipJx9JkBIilUqRSqWoq6ujoqIi33EkSVLC7GhNpZNPPpmf/OQnFBUVMXz4cM4999zBjCepDzYMJEmSJA24Ha2pdNhhh3XtkCBpaPCRBEmSJEkDzjWVpN3PTjUMQgjTQghP9DF+bgjhf0MIS0IIn9nl6SRJkiTtEVxTSdr97LBhEEL4R+AHwMhtxocD3wLOBk4FKkMI7n0iSZIkqU+pVIr6+npWrFhBfX29zQJpiNuZGQZ/BC7sY7wCeD7G+HqMsQ34FfChXRlOkiRJkiTlxw4XPYwx3h9CKO/j0D7AG93evwns29/n1NXVveNwA621tXVI5hosSa7f2q09aaw9mbVLkiS9F+9ll4QNwJhu78cAzf2dPBS3cUv69nJJrt/arT1prH1o1r506dJ8R5AkSerXe2kY1AFHhRDGAm/R8TjCN3ZJKkmSlGghhGnAjTHG00IIxwHfAbYAm4BLYowvb3P+b+j4ZQbA6hjjpYMaWJKkPdA7bhiEEC4GRscYq0MI1wKP0LEWwu0xxhd3dUBJkpQsnQsufwp4u3Po28DVMcbfhRCuAL4AXNvt/JFAQYzxtMHOKknSnmynGgYxxnpgeufru7uN1wA1A5JMkiQl1dYFl3/Y+f6iGOOaztfDgNZtzn8fUBxCeLTz+D/HGJ/q64OH4noWSV9nI8n1W7u1J4217361v5dHEiRJkna5bRdc3tosCCF8ELiK3rsytdDxWOQPgKOAh0IIIca4edvPHorrWQzldTYGQ5Lrt3ZrTxprH5q1b29NJRsGkiRpyAsh/A1QBXw0xvjqNoefpWOr5xzwbAhhPTABaBzkmJIk7VEK8x1AkiRpe0IIf0vHzILTYowv9HHKZcA3O889mI6tn9f0cZ4kSXoHnGEgSZKGrBBCEfAfQAPw4xACwJMxxi+HEO4CvgjcBswPIfwKyAGX9fU4giRJemdsGEiSpCGn+4LLwNh+zrmk29uLBzqTpF2vqamJxx57jNmzZ7N27VoeeughCgoKGDZsGBdccAGjR4/Od0Qp0WwYSJIkSRp0tbW1LFu2jOHDhwPw8MMPc84553DQQQfxzDPPUFtby4wZM/KcUko21zCQJEmSNOhKSkqYNWtW1/uPf/zjHHTQQQC0t7czbJi/25TyzYaBJEmSpEGRyWQoLy9n0qRJzJw5k5qamq5jY8aMAaCxsZH//d//Zfr06f19jKRBYsNAkiRJ0oDLZDJUVlaSzWbJ5XJks1nmzp3LunXrus75wx/+wKJFi7j44ovZe++985hWEriGgSRJkqRBUFVVRUtLS4+x1tZWGhsbAVi2bBlLly5l9uzZjBo1Kh8RJW3DhoEkSZKkAdfQ0NDneFtbG+3t7Tz00EPsu+++3HvvvQCUlZXx4Q9/eDAjStqGDQNJkiRJA660tJRsNttjrLm5mcWLF1NYWMgXvvCFPCWT1B/XMJAkSZI04NLpNMXFxT3GiouLSafTeUokaUecYSAlTHt7O9/97nfZsGEDBQUFzJo1i7/4i7/oOr5gwQKy2SxFRUVMmzbNqYCSJGmXSKVSQMdaBg0NDZSWlpJOp7vGJQ09zjCQEmb58uVs2bKFuXPncvbZZ/PAAw90HVu5ciXZbJZ/+Id/4HOf+xz/8z//02txIkmSpHcrlUpRX1/PihUrqK+vt1kgDXHOMJASZu3atey1117cdtttFBUV8dZbb3Uda2hoYOTIkcyfP58RI0YwfPhwVq1axQknnJDHxJIkSZLywRkGUkJceeWVDBs2jMbGxq5ti84880wANm/eDEBJSQlvvfUWs2bNYubMmWzcuLFHQ0GSJElScjjDQEqAK6+8knnz5gFQWFjIm2++yd133w3A+PHjGTas4z8Fo0ePZty4cXz/+99n1KhRXeOSJEmSkscZBlICVFdXd71+++23mTBhAgC//vWvKSgooL29HYBhw4bx5ptvcu2113LRRRexefPmrnMlSZIkJYu/PpQSYMuWLV2vX3jhBSZOnMjcuXMBGDlyJPfeey/jx4/ntNNOY/jw4dx4440UFBQwfvx4xowZk6/YkiRJkvLIhoGUAAUFBeRyOaBjYcNRo0axcOFCDj30UG644QY++clPAh2zD0466SSmT59Oa2srCxYs4MADD8xndEmSJEl5YsNASoC99967a/HCVatWccQRRzBnzhyKioqYMWMGS5YsYezYsRx99NG8+uqr3HrrrRQVFXHWWWdRWOiTS5IkSVIS2TCQEuDtt9/uep3L5Vi0aBHQMfPg+9//PuPGjes6fu655w56PkmSJElDj786lBKgtLT0HY1LkiRJkg0DKQHS6TTFxcU9xoqLi0mn03lKJEmSBE1NTcyfP7/H2MMPP8wzzzyTn0CSevCRBCkBUqkUAFVVVTQ0NFBaWko6ne4alyRJGmy1tbUsW7aM4cOHAx2PUC5cuJD169f3eFxSUv44w0BKiFQqRX19PStWrKC+vt5mgSRJyquSkhJmzZrV9b6trY1TTz2VY489No+pJHVnw0CSJEnSoJs4cSJFRUVd70tKSjj00EPzmEjStmwYSJIkSRoUmUyG8vJyJk2aRHl5OQsXLsx3JEnbYcNAkiRJ0oDLZDJUVlaSzWbJ5XJks1nmzp3LunXr8h1NUj9sGEiSJEkacFVVVbS0tPQYa21tpbGxMU+JJO2IDQNJkiRJA66hoaHXWHNzM/Pmzesxdtppp3HiiScOVixJ22HDQJIkSdKAKy0tfUfjkvLPhoEkSZKkAZdOpykuLu4xVlxcTDqdzlMiSTtiw0CSJEnSgEulUlRXV1NWVkZBQQFlZWVUV1eTSqXyHU1SP4blO4AkSZKkZEilUqRSKerq6qioqMh3HEk74AwDSZIkSZLUiw0DSZIkSZLUiw0DSZIkSZLUiw0DSZIkSZLUiw0DSZIkSZLUyw53SQghFAK3AO8DNgGXxxif73b8H4CLgXbg32KMDwxQVkmSJEmSNEh2ZobBBcDIGOMHgH8Cvrn1QAhhP+Aa4APA2cDNAxFSkiRJkiQNrh3OMABOBh4GiDE+FUI4sduxt4EssHfnn/b+PqSuru49xBwYra2tQzLXYEly/dZu7Ulj7cmsXZIk6b3YmYbBPsAb3d5vCSEMizFu7nzfCKwEioCv9fchFRUV7zrkQKmrqxuSuQZLkuu3dmtPGmsfmrUvXbo03xEkSZL6tTOPJGwAxnS/pluz4BxgAnA4UApcEEJ4/66NKEmSJGlP1NTUxPz58wF47bXXuP3227njjjtYtGgRuVwuv+Ek7VTDoBaYCRBCmA4s73bsdWAjsCnG2Ao0A/vt6pCSJEmS9iy1tbXU1NSweXPH7yIfeeQRTj/9dC699FIAVq1alc94kti5hsEDQGsI4X+AbwH/J4RwbQjhvBjjL4H/BZ4KISwBngUWD1xcSZIkSXuCkpISZs2a1fV+zZo1lJWVAXDkkUfywgsv5CuapE47XMMgxtgO/N02w6u6Hf8y8OVdnEuSJEnSHiaTyVBVVUVDQwOlpaVcf/31XcdyuRwFBQUAjBgxgk2bNuUppaStdmbRQ0mSpEEVQpgG3BhjPC2EcCQwH8gBfwA+2/kLja3njgIWAAcCbwKfjjG+OvipJW1PJpOhsrKSlpYWALLZLHPnzuWaa64B6GoWAGzatImRI0fmJaekP7NhICVMLpdj0aJFvPzyyxQVFXHeeecxduxYANauXcvDDz/cdW5TUxMXXXQRRx55ZL7iSkqgEMI/Ap+iY/tmgH8HvhhjfCKE8D3gfDoemdzq74HlMcbrQwgXAV8ErhnMzJJ2rKqqqqtZsFVrayuNjY0ATJgwgfr6esrLy3n++ecpLy/PQ0pJ3dkwkBLmxRdfZPPmzcyZM4empiYeffRRLrroIgAOOuggZs+eDcCKFSvYZ599bBZIyoc/AhcCP+x8PxV4svP1Q8DZ9GwYnAx8vdvx/9vfB9fV1e3SoLtCa2vrkMw1WJJcf9Jqb2ho6HO8ra2Nuro6jjjiCB588EHa29sZM2YMhx9++B75/Una33t31r771W7DQEqYdevWMWXKFAAOPfRQXnrppV7ntLW18cQTT3StUixJgynGeH8IobzbUEGMcev+am8C+25zyT7AG9s53qWiomJXxdxl6urqhmSuwZLk+pNWe2lpKdlstsdYc3Mzixcv5tZbbwXg/e/f83doT9rfe3fWPjRrX7p0ab/HdmaXBEl7gEwmQ3l5Offccw9XXHEFmUwG6HhesL29vce5v/3tb5k4cSLFxcX5iCpJ2+r+H6kxdGzj3N2GzvH+jksaAtLpdK97i+LiYtLpdJ4SSdoRGwZSAmxdZCibzbJp0ybeeOMNKisryWQy5HI5Cgt7/qdg+fLlnHDCCXlKK0m9/DaEcFrn63OAX25zvBaYuZ3jkoaAVCpFdXU1ZWVlFBQUUFZWRnV1NalUKt/RJPXDhoGUAN0XGWpoaOCoo46ipaWFm2++mfHjx/c4t7W1lc2bN7Pvvv3O6JWkwfYPwL+EEJYAewH3AYQQHg0h7AXMAyaFEH4FVAL/krekkrYrlUpRX1/PihUrqK+vt1kgDXGuYSAlQPdFhlatWsWHP/xh5s6dSy6XY9q0aSxZsoSxY8ey77778pOf/IQNGzYwf/58d0mQlDcxxnpgeufrZ4FT+zjn7M6XbcBfD1o4SZISwoaBlADdFxk65phjeOmll7jllls48cQTed/73te1SwLAFVdcAbhLgiRJkpR0PpIgJUD3RYZKS0t5/vnnKS4u5nOf+9x2d0n4yEc+MthRJUmSJA0RNgykBEilUnz605+mqKiIESNG0NbWxqc//WlSqZS7JEiSJEnqkw0DKQEymQx33nknW7ZsYdOmTQwfPpw777zTXRIkSZIk9cs1DKQE2HaXhBACK1as4Oabb+Zzn/tcj3PdJUHSnuy00/KdoLeWllKSPKEryfVbe75T5Ie15ztFfgzl2r/5zf6POcNASoBtd0nYvHkzc+bM4X3vex8zZsxgyZIlxBgBWL9+Pfvtt1++okqSJEkaIpxhICVA910ScrkcixYtAqCsrIxx48Yxbty4rnMPOeSQHrsmSNKe5Ikn8p2gt7q6BioqKvIdI2+SXL+1W3vSWPvQrH3p0v6POcNASoDuuyRsVVxcTDqdzlMiSZIkSUOdDQMpAVKpFNXV1ZSVlVFQUEBZWRnV1dWkUql8R5MkSZI0RPlIgpQQqVSKVCpFXV3dkJ0OJUmSkmHLli3cf//9vP7664wYMYKZM2ey//775zuWpG04w0CSJEnSoHrhhRfYa6+9uPzyyznnnHN46KGH8h1JUh9sGEiSJEkaVBs2bODII48EYNy4cbz66qt5TiSpLz6SIEmSJGlQZDIZqqqqGDduHCEEzjnnHE477TTefPNN2tvbKSz095nSUGLDQJIkSdKAy2QyVFZW0tLSQmNjI+PGjePJJ59k/fr1TJgwwWaBNAT5b6UkSZKkAVdVVUVLSwsABx98MKtXr+YHP/gBd911FyUlJXlOJ6kvzjCQJEmSNOAaGhq6Xr/22mucfvrpnHLKKbS2tjJjxow8JpPUHxsGkiRJkgZcaWkp2WwWgJaWFu666y4AysrKGDNmTD6jSeqHjyRIkiRJGnDpdJri4uIeY8XFxaTT6TwlkrQjNgwkSZIkDbhUKkV1dTVlZWUUFBRQVlZGdXU1qVQq39Ek9cNHEiRJkiQNilQqRSqVoq6ujoqKinzHkbQDzjCQJEmSJEm92DCQJEmSJEm9+EiClDC5XI5Fixbx8ssvU1RUxHnnncfYsWO7jj/33HM8+eSTAEyYMIGZM2dSUFCQr7iSJEmS8sQZBlLCvPjii2zevJk5c+Zw5pln8uijj3Yd27RpE4sXL+biiy/m8ssvZ7/99qOlpSWPaSVJkiTlizMMpIRZt24dU6ZMAeDQQw/lpZde6jrW2NjI+PHjefTRR3n99dc5/vjj2XvvvfMVVZIkSVIeOcNASohMJkN5eTn33HMPV1xxBZlMBoCCggLa29sBaGlpYfXq1Zx55pmkUimefvpp1q9fn8/YkiRJkvLEGQZSAmQyGSorK2lpaeGYY47hjTfeoLKyEuhY06CwsKN3WFxczCGHHMLo0aMBKC0tZe3atey///55yy5JkiQpP5xhICVAVVVV11oEDQ0NHHXUUbS0tHDzzTczfvz4rvMmTJjAK6+8QktLC+3t7bz44osccMAB+YotSZIkKY+cYSAlQENDQ9frVatWccQRRzBnzhwAZsyYwZIlSxg7diwhBM444wwWLFgAwMSJEznwwAPzklmSJElSftkwkBKgtLSUbDYL/HlbRYCysjLGjRvHuHHjus6dPHkykydPzktOSZIkSUOHjyRICZBOpykuLu4xVlxcTDqdzlMiSZKUZO3t7dx///3cdttt3HHHHaxbty7fkST1wYaBlACpVIrq6mrKysooKCigrKyM6upqUqlUvqNJkqQEWrNmDe3t7cyZM4cPfehDPP744/mOJKkPO3wkIYRQCNwCvA/YBFweY3y+2/FzgC8DBcBS4LMxxtzAxJX0bqVSKVKpFHV1dVRUVOQ7jiRJSrAxY8awfv16crkcmzZt6tqxSdLQsjP/Zl4AjIwxfgD4J+CbWw+EEMYANwEfizFOA+qBcX19iCRJkqRky2QylJeXM2PGDGpra/na175GTU0N06ZNy3c0SX3YmYbBycDDADHGp4ATux37ILAc+GYI4ZfAyzHGV3d5SkmSJEm7tUwmQ2VlJdlslunTp7Ny5UrS6TTjx49n4cKFbN68Od8RJW1jZ3ZJ2Ad4o9v7LSGEYTHGzXTMJvgwcBzwFvDLEMKSGOOz235IXV3drsi7S7W2tg7JXIMlyfVbu7UnjbUns3ZJGkqqqqpoaWkBYOPGjbS3t9PS0sJXv/pVrrrqKtrb2/OcUNK2dqZhsAEY0+19YWezAGA98L8xxrUAIYRf0NE86NUwGIrPTCf9We4k12/t1p401j40a1+6dGm+I0jSoGloaOh6/dRTT3H++edz6aWXUlRUxBlnnMFee+2Vx3SS+rIzDYNa4Fzg/4UQptPxCMJWvwEmhxDGAc3AdODWXZ5SkiRJ0m6ttLSUbDYLQFtbG//1X/8FQFlZGbfe6v9CSEPRzjQMHgDOCiH8Dx07IVwaQrgWeD7G+NMQwlzgkc5z/1+M8Q8DlFXSLpDL5Vi0aBEvv/wyRUVFnHfeeYwdO7br+HPPPceTTz4JwIQJE5g5cyYFBQX5iitJkvYQ6XSaysrKrscSAIqLi0mn03lMJWl7dtgwiDG2A3+3zfCqbsfvAe7ZxbkkDZAXX3yRzZs3M2fOHJqamnj00Ue56KKLANi0aROLFy9m9uzZFBcXU1tbS0tLC3vvvXeeU0uSpN1dKpUCOtYyaGhooLS0lHQ63TUuaejZmRkGkvYg69atY8qUKQAceuihvPTSS13HGhsbGT9+PI8++iivv/46xx9/vM0CSZK0y6RSKVKp1JBeX0bSn+3MtoqS9gBb9z2+5557uOKKK8hkMgAUFBR0rUrc0tLC6tWrOfPMM0mlUjz99NOsX78+n7ElSZIk5YkzDKQE2LrvcUtLC8cccwxvvPEGlZWVQMeaBoWFHb3D4uJiDjnkEEaPHg10LE60du1a9t9//7xllyRJkpQfzjCQEqD7vscNDQ0cddRRtLS0cPPNNzN+/Piu8yZMmMArr7xCS0sL7e3tvPjiixxwwAH5ii1JkiQpj5xhICVA932PV61axRFHHMGcOXMAmDFjBkuWLGHs2LGEEDjjjDNYsGABABMnTuTAAw/MS2ZJ6i6EMBuY3fl2JHAccFCMsbnz+LeBk4E3O885P8b4xiDHlCRpj2LDQEqA7vseb91WETr2PR43bhzjxo3rOnfy5MlMnjw5LzklqT8xxvnAfIAQwneB27c2CzpNBWbEGNcNfjpJkvZMNgykBHDfY0l7ihDCicCkGONnu40VAkcB1SGE8cBtMcbb+7q+rq5ucIK+A62trUMy12BJcv3Wbu1JY+27X+02DKQEcN9jSXuQfwb+ZZuxvYHvAP8OFAH/HUJ4Jsa4bNuLh+I2bknfXi7J9Vu7tSeNtQ/N2pcuXdrvMRsGUkK477Gk3V0IYT8gxBj/e5tDLcC3Y4wtnec9DrwP6NUwkCRJO8+GgSRJ2l18CPh5H+NHA/eGEI6nYweok4E7BzOYJEl7IhsGkiRpdxGAF7rehHAt8HyM8achhB8CTwF/Au6KMa7IU0ZJkvYYNgwkSdJuIcZ40zbv/32bYzf1ukjSkLR69WqefvppADZv3szatWv5/Oc/z8iRI/OcTFJ3NgwkSZIkDarDDz+c/7+9+4+TurrzfP+qblQoAWPbSccEu9oF9tCDiAaHRPMDjGbZCQljZjOOaxk30rHxJrnqJI87m0wns9ld686d3c0um5mdcdqAer2luNmJMeJo2keIO4mSIZJZxzDN8TKBLoWIQQGVkoama//opi1ofgnd/S36+3o+Hnmk63u+Xbw/XdJ1+NT5nu/HP/5xAB599FEuvfRSmwVSDapLOoAkSZKkdNq2bRu//vWvmTdvXtJRJB2BDQNJkiRJY6JYLNLS0sLs2bNpaWnh/vvvZ8GCBUnHknQUNgwkSZIkjbpisUh7ezs9PT1UKhW2b99OT08PTz/9dNLRJB2FDQNJkiRJo66jo4NyuTz0OJfL8Y//+I90dHQkmErSsdgwkCRJkjTqSqXSIY/PO+88du7cOey4pNrhXRIkSZIkjbrm5mZ6enqGHh+8FCGXyyUVSdJxuMJAkiRJ0qgrFApks9lDjmWzWQqFQkKJJB2PDQNJkiRJoy6fz9PZ2UkulyOTyZDL5ejs7CSfzycdTdJReEmClDKVSoXVq1ezfft26uvrWbJkCQ0NDUPjjz32GC+88AJnnnkmANdddx0TJ05MKq4kSRpH8vk8+Xye7u5uWltbk44j6ThsGEgps3XrVvr6+mhra+PFF1+kq6uL6667bmj8V7/6FTfccMOwJYOSJEmS0sWGgZQyO3bsYM6cOQBMmzaNbdu2DY1VKhVeffVVHnnkEfbs2cOll17KpZdemlRUSZIkSQlyDwMpJYrFIi0tLaxatYply5ZRLBYByGQy9Pf3A7Bv3z7mz5/P7/zO75DP5/nZz37G9u3bk4wtSZIkKSGuMJBSoFgs0t7eTrlcZtasWezevZv29nZgYFVBXd1A7/CMM87g/e9/P2eccQYAF154IS+99BJNTU2JZZckSZKUDFcYSCnQ0dFBuVwGoFQqMXPmTMrlMsuXLz+kGfDKK6+wcuVK+vv7OXDgAKVSifPPPz+p2JIkSZIS5AoDKQVKpdLQ1xs3bmT69Om0tbUBsGjRItauXUtDQwMhBC6++GJWrFhBXV0dc+fO5V3veldSsSVJkiQlyIaBlALNzc309PQAb91WESCXy9HY2EhjY+PQuR/84Af54Ac/mEhOSZIkSbXDSxKkFCgUCsNuk5jNZikUCgklkiRJklTrbBhIKZDP5+ns7CSXy5HJZMjlcnR2dpLP55OOJkmSJKlGeUmClBL5fJ58Pk93dzetra1Jx5EkSSn34x//mOeff54DBw5w2WWX8b73vS/pSJIOY8NAkiRJ0ph6+eWX2bZtG0uXLmX//v08/fTTSUeSdAQ2DKSUObjp4fbt26mvr2fJkiU0NDQMO+f+++8nhMBll12WUFJJkjRevfTSS7zrXe/iwQcfpLe3l4997GNJR5J0BO5hIKXM1q1b6evro62tjauvvpqurq5h56xZs4Y333wzgXSSJCkNent72bZtG7/7u7/L4sWL+e53v0ulUkk6lqTDuMJASpkdO3YwZ84cAKZNm8a2bdsOGf+Hf/gHMpkMM2bMSCKeJEkax4rFIh0dHcycOZMzzzyTuro68vk8EyZMoFwuc/bZZycdUVIVVxhIKVEsFmlpaWHVqlUsW7aMYrEIQCaTob+/Hxi4nvC5557jyiuvTDKqJEkah4rFIu3t7fT09FAqlTjvvPNob2/n3nvvZd++fUyaNCnpiJIO4woDKQUOvkGXy2VmzZrF7t27aW9vBwb2K6irG+gdPvvss7z++uvce++97Nq1i/r6et7xjne42kCSJJ2yjo4OyuUyAM8//zy5XI58Ps8zzzzDbbfdNjQfkVQ7bBhIKVD9Bl0qlQghsGHDBpYvX87tt98+dF71hkNPPvkkkydPtlkgSZJGRKlUOuTxE088AQysdvzTP/3TJCJJOg7beFIKVL9Bb9y4cWjTw7lz57Jo0SLWrl1LjDHBhJIkabxrbm5+W8clJc8VBlIKNDc309PTA7x1W0WAXC5HY2MjjY2Nw75n4cKFYxlRkiSNc4VCYegSyYOy2SyFQiHBVJKO5bgrDEIIdSGEO0MIa0MIT4YQhq1PHjznsRDCLaMTU9KpKBQKZLPZQ475Bi1JksZSPp+ns7OTXC5HJpMhl8vR2dlJPp9POpqkoziRSxKuASbGGC8HvgJ88wjn3AGcO5LBJI0c36AlSVItyOfzbNmyhQ0bNrBlyxbnIlKNf/OmdQAAIABJREFUO5FLEj4EPA4QY/xpCOGy6sEQwqeB/oPnHE13d/fJZhw1e/furclcYyXN9aex9ve973089thj7N27l4kTJwK1+fdyNKXxdT/I2tNZuyRJ0qk4kYbBVGB31eMDIYQJMca+EMJFwPXAp4E/OtaTtLa2nnzKUdLd3V2TucZKmuu3dmtPG2uvzdrXr1+fdARJkqSjOpGGwWvAlKrHdTHGvsGvbwTeC6wBWoB9IYQtMcZjrjaQJEmSJEm17UQaBk8BnwT+ewjhA8BzBwdijH9w8OsQwjeAl2wWSJIkSZJ0+juRhsFDwMdCCE8DGeCmEMKXgE0xxu+PajpJkiRJkpSI4zYMYoz9wOG3S9x4hPO+MUKZJEmSJElSwk7ktoqSJEmSJCllbBhIkiRJkqRhbBhIkiRJkqRhTmTTQ0mSJEkaUX/5l3/JWWedBcC5557Lb//2byecSNLhbBhIKVOpVFi9ejXbt2+nvr6eJUuW0NDQMDS+bt06nn32WQCuuOIKZs+enVRUSZI0Th04cACAz372s8kGkXRMXpIgpczWrVvp6+ujra2Nq6++mq6urqGxcrnMM888w9KlS7nxxhvp6uqiUqkkmFaSJI1Hu3btYv/+/dx3333ce++9vPjii0lHknQENgyklNmxYwczZswAYNq0aWzbtm1oLJvNcsstt1BfX88bb7zBhAkTyGQySUWVJEnjTLFYpKWlhU9/+tN8//vfJ5PJ8IlPfILvfve79Pf3Jx1P0mG8JEFKiWKxSEdHB3PnzuXP/uzP+PznP08+nyeTydDf309d3UD/sK6ujnXr1vHkk08yf/78hFNL0ltCCD8HXht8uDnGeFPV2M3AMqAPuCPGuDqBiJKOoVgs0t7eTrlcpr6+nh/96Ec89dRTdHZ2MmnSJF5//XXOOeecpGNKqmLDQEqB6jfoWbNmsXv3btrb24GBPQ0ONgsOmj9/PvPmzaNYLLJ582YuvPDCJGJL0pAQwkQgE2NceISxdwO3ApcBE4GfhBCeiDH2jm1KScfS0dFBuVwG4NJLL6WpqYlHH32UO+64gy984QtMmTIl4YSSDmfDQEqB6jfoUqlECIENGzawfPlybr/99qHzduzYwQ9/+EOuvfZa6urqqK+v95IESbViLpANIXQxMH/5wxjjTwfH5gNPDTYIekMIm4CLgZ8d/iTd3d1jlfeE7d27tyZzjZU015+22kul0tDXf/d3f8c111zD0qVLqVQqzJ07lxhjgunGTtpe92rWfvrVbsNASoHqN+iNGzcyffp02traAFi0aBFr166loaGBEAJNTU2sWLGCTCbDjBkzaGlpSSi1JB2iDPwn4NvATOCxEEKIMfYBU4HdVee+DhxxXXNra+to53zburu7azLXWElz/Wmrvbm5mZ6eHmDgLgl/9Vd/BUAul2PlypVJRhtTaXvdq1l7bda+fv36o47ZMJBSoPoN+uBtFWHgDbqxsZHGxsahcxcuXMjChQuTiClJx/I8sCnGWAGeDyG8ApwPvMDAvgbVa5mnALvGPqKkYykUCkOXSB6UzWYpFAoJppJ0LDYMpBSofoPOZDIsXryY888/n+nTp/Pqq6/S0NAwdO66det49tlnAbjiiiuYPXt2UrElqdpSYA7w+RDCexhYVfCrwbF1QGFwn4OzgFbgF4mklHRU+XweGLhUslQq0dzcTKFQGDouqfZ4W0UpBfL5PJ2dneRyOWbNmsU555zDggULyOfzdHV1DZ1XLpd55plnWLp0KTfeeCNdXV1UKpUEk0vSkBXAO0IIPwEeZKCBcGsIYUmM8SXgW8CPgTVAR4xxb3JRJR1NPp9ny5YtbNiwgS1bttgskGqcKwyklMjn8+TzeR544AHmzJnDRRddBMC2bduGzslms9xyyy3U1dWxa9cuJkyY4KaHkmpCjHEfcP1hh5+uGr8LuGtMQ0mSNM65wkBKiWKxSEtLC6tWrWLZsmUUi0UAMpkM/f39Q+fV1dWxbt06VqxYwZw5c5KKK0mSJClhrjCQUqBYLA7tYTBr1ix2795Ne3s7MLAJYl3dob3D+fPnM2/ePIrFIps3b+bCCy9MIrYkSZKkBLnCQEqBjo6OoR2JS6USM2fOpFwus3z5cpqamobO27FjBw8++OBQE6G+vt5LEiRJkqSUcoWBlAKlUmno640bNzJ9+nTa2toAWLRoEWvXrqWhoYEQAk1NTaxYsYJMJsOMGTNoaWlJKLUkSZKkJNkwkFKgubmZnp4eYOAShNWrVwOQy+VobGyksbFx6NyFCxeycOHCJGJKkiRJqiFekiClQKFQIJvNHnIsm81SKBQSSiRJkiSp1tkwkFIgn8/T2dlJLpcjk8mQy+Xo7Oz03seSJEmSjspLEqSUyOfz5PN5uru7aW1tTTqOJEmSpBrnCgNJkiRJkjSMKwyklDm46eH27dupr69nyZIlNDQ0DI2vW7eOZ599FoArrriC2bNnJxVVkiSNc3v27KGzs5PPfOYzh2zCLKk2uMJASpmtW7fS19dHW1sbV199NV1dXUNj5XKZZ555hqVLl3LjjTfS1dVFpVJJMK0kSRqvDhw4wOrVq5kwwc8wpVplw0BKmR07djBjxgwApk2bxrZt24bGstkst9xyC/X19bzxxhtMmDCBTCaTVFRJkjSOdXV1MW/ePKZMmZJ0FElHYcNASolisUhLSwurVq1i2bJlFItFADKZDP39/UPn1dXVsW7dOlasWMGcOXOSiitJksahg/OR66+/njvvvJO//du/TTqSpGOwYSClQLFYpL29nZ6eHnp7e9m9ezft7e0Ui0UqlQp1dYf+Kpg/fz5f/vKXKZVKbN68OaHUkiRpPKmej1x66aU0NDSwZs0aXnjhBR566CHeeOONpCNKOowNAykFOjo6KJfLAJRKJWbOnEm5XGb58uU0NTUNnbdjxw4efPDBoSZCfX29lyRIkqQRUT0fufvuu7nnnntYuXIlW7du5VOf+hSTJ09OOKGkw7nDiJQCpVJp6OuNGzcyffp02traAFi0aBFr166loaGBEAJNTU2sWLGCTCbDjBkzaGlpSSi1JEkaT6rnI9V6e3vHOImkE2XDQEqB5uZmenp6gLduqwiQy+VobGw85DZGCxcuZOHChUnElCRJ41j1fKTaj370I2+pKNUoL0mQUqBQKJDNZg85ls1mKRQKCSWSJElp43xEOv24wkBKgXw+DwxcO1gqlfi93/s95s6dy/79+3n11VdpaGgYOnft2rVs2LABgBkzZrjaQJIkjYjD5yPNzc0UCoWh45Jqjw0DKSXy+Tz5fJ4nnniCPXv2cM011/Diiy/S1dXFddddB8DOnTt57rnn+NznPkcmk+Huu++mtbX1kI0RJUmSTtbB+Uh3dzetra1Jx5F0HF6SIKXMjh07mDFjBgDTpk1j27ZtQ2NTp07lhhtuoK6ujkwmw4EDB5gwwb6iJEmSlEZj9i+BWlzVXC43c9hlVKmS5vrTWPv27dvZvHkzixa9xr//95upVN5JU1MTl1+e4cor+6lU6oB6IAtUmD79Cerr302xeF7CyUdOGl/3g6w96RRH9s1vJp1AkiTp6PzoUEqB7du38/zzkf7+fnp766mre5Pu7jg4WhlsFgyoq+tj1qyH6es7k+efX5xMYEmSJEmJG7OGwZNPjtWfdOK6u0upvnYqzfWnrfaWlvfT3z9wG6NSqZUQAhs2fI/Jky/jootu54//eOC8SqVCsbiKlpYWPvShDyWYeHSk7XWvZu21Wfv69UknkCRJOjpXGEgpUCqVhr7euHEj06dPp62tDYBFixaxdu1aGhoa6O/vZ8uWLfT19bFp0yYArrrqKi644IJEckuSJElKznEbBiGEOuDPgblAL/C5GOOmqvHfB64bfPjXMcZ/OxpBJZ285uZmenp6hh2fMGECdXV1XH755UPHrrrqqkNuq2izQJIkSUqnE7lLwjXAxBjj5cBXgKEtmkII/wTIA1cAHwD+WQjh4tEIKunkFQoFsoO7vs2aNYsJEybwwAMP8Ju/+Zt0dXUNnXfwtopLly6lra2NX/7yl2zfvj2p2JIkSZISdCINgw8BjwPEGH8KXFY19gLwz2OMB2KMFeAMYO+Ip5R0SvL5PJ2dneRyOZqbm9m1axednZ20tbV5W0VJkiRJR3Qi/xKYCuyuenwghDAhxtgXY9wP7AghZID/CPxdjPH5Iz1Jd3f3qacdYXv37q3JXGMlzfWnsfZt27axb98+zjrrLHbu3Mm2bdvo7u7mwIEDbNiwgbq6t/qHlUqFZ599lokTJ/Lyyy/z8ssvJ5h85KTxdT/I2tNZuyRJ0qk4kYbBa8CUqsd1Mca+gw9CCBOBlcDrwOeP9iS1uEN1d3d3TeYaK2muP221F4tFvvGNb1Aul+nt7WXPnj184xvf4D3veQ/19fXMnj176Ny+vj4efvhhJk+ezOLFiw9pJJzu0va6V7P22qx9vbdJkCRJNexE/iXwFPBxgBDCB4DnDg4Mrix4GHg2xrgsxnhgVFJKOiUdHR2Uy2Vg4I4JM2fOpFwus3z5cpqamobOq1QqrFq1iqamJj75yU+Oq2aBJEmqHf39/Tz88MOsXLmSlStXjpvVjNJ4cyIrDB4CPhZCeBrIADeFEL4EbALqgQXAWSGE3xo8/6sxxrWjklbSSfG2ipIkqZb86le/AmDp0qVs2bKFNWvWcN111x3nuySNteM2DGKM/cAthx3eWPX1xBFNJGnEVd9WsVKpsHr1agByuRyNjY00NjYOnfu1r30tkYySJCk93vve9xJCAGDXrl1MnOg/KaRa5PbnUgoUCgXa29spl8tkMhkWL17M+eefz/Tp03n11VdpaGgYOnft2rVs2LABgBkzZrBw4cKEUkuSpPGmWCzS0dFBqVSiubmZW2+9ld7eXq699tqko0k6Ai9QllKg+raKs2bN4pxzzmHBggXk83m6urqGztu5cyfPPfccS5cupa2tjV/+8pds3749weSSJGm8KBaLtLe309PTQ6VSoaenh69//eu85z3v4ZFHHmHfvn1JR5R0GFcYSCmRz+fJ5/M88MADzJkzh4suuggYuN3iQVOnTuWGG24Y2uzwwIEDTJjgrwlJknTqqjdhvvjii5k6dSo/+clPuOOOO/jiF79IJpNJOKGkw7nCQEqJYrFIS0sLq1atYtmyZRSLRQAymQz9/f0A1NfXk81mqVQqdHV18e53v5vzzjsvydiSJGmcqN6Eubu7m/PPP5+bbrqJBQsWsGjRIs4444wE00k6Ej86lFLg4BLAcrnMrFmz2L17N+3t7cDAJojVt0/s6+vj4Ycf5swzz2Tx4sVJRZYkSeNM9SbM+/fv5zvf+Q4wsAnzt7/97SSjSToKVxhIKVC9BLBUKjFz5kzK5TLLly+nqalp6LxKpcKqVatoamrik5/85CGNBEmSpFNRKBTIZrOHHMtmsxQKhYQSSToeVxhIKVC9BHDjxo1Mnz6dtrY2ABYtWsTatWtpaGigv7+fLVu20NfXx6ZNmwC46qqruOCCCxLJLUmSxo98Pg9wyF0SCoXC0HFJtceGgZQC1UsAK5UKq1evBgaWADY2NtLY2Dh07te+9rVEMkqSpPHv4CbM3d3dtLa2Jh1H0nG43lhKAZcASpIkSXq7bBhIKZDP5+ns7CSXy5HJZMjlcnR2droEUJIkSdJReUmClBIuAZQkSZL0dtgwkCRJNS2EcAawEmgBzgLuiDF+v2r894HPAb8ePLQsxhjHOqckSeONDQNJklTrbgBeiTF+JoTQAPwv4PtV4/OAG2OM6xNJJ0nSOGXDQJIk1brvAP9j8OsM0HfY+DzgqyGEdwOPxhj/+GhP1N3dPToJT8HevXtrMtdYSXP91m7taWPtp1/tNgwkSVJNizG+ARBCmMJA4+Dw+7+uAv4b8BrwUAjhEzHG1Ud6rlrcwyXte8ukuX5rt/a0sfbarH39+qMv0PMuCZIkqeaFEC4AfgTcF2O8v+p4BlgeY9wRY9wHPApcmlBMSZLGFVcYSJKkmhZCaAK6gC/GGH942PBU4BchhFZgD/BRBjZIlCRJp8iGgSRJqnV/CJwLfD2E8PXBY3cBZ8cYO0MIf8jA6oNe4Icxxr9OKKckSeOKDQNJklTTYoy3AbcdY/w+4L6xSyTpVPX39/PQQw+xa9cu+vr6+MhHPkIIIelYkg5jw0CSJEnSmOrp6WHSpEl86lOf4s033+TOO++0YSDVIBsGkiRJksbUtGnThhoElUqFujr3YpdqkX8zJUmSJI2JYrFIS0sLl1xyCSEE7rvvPr7zne/w0Y9+NOloko7AhoEkSZKkUVcsFmlvb6enp4dKpcLOnTt5+umnKZfLzJkzJ+l4ko7AhoEkSZKkUdfR0UG5XAbg7LPP5jOf+Qw/+MEP+JM/+ZOEk0k6GhsGkiRJkkZdqVQa+vrDH/4wkyZNYsGCBVx55ZXcc8897N+/P8F0ko7ETQ8lSZIkjbrm5mZ6enoAePzxx3n88ccByOVy3H333UlGk3QUrjCQJEmSNOoKhQLZbPaQY9lslkKhkFAiScdjw0CSJEnSqMvn83R2dpLL5chkMuRyOTo7O8nn80lHk3QUXpIgSZIkaUzk83ny+Tzd3d20trYmHUfScbjCQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSZIkDWPDQJIkSVIiXnzxRe65556kY0g6iglJB5AkSZKUPk899RR///d/zxlnnJF0FElH4QoDSZIkSWPu3HPP5dprr006hqRjOO4KgxBCHfDnwFygF/hcjHFT1fjNwDKgD7gjxrh6lLJKkiRJGid+4zd+g127diUdQ9IxnMgKg2uAiTHGy4GvAN88OBBCeDdwK/BBYBHwxyGEs0YjqCRJkqTTW7FYpKWlhdmzZ9PS0sL3vve9pCNJOoYT2cPgQ8DjADHGn4YQLqsamw88FWPsBXpDCJuAi4GfHf4k3d3dIxB3ZO3du7cmc42VNNdv7daeNtaeztolqZYUi0Xa29spl8sA9PT08NWvfpXbbrst4WSSjuZEGgZTgd1Vjw+EECbEGPuOMPY6cM6RnqS1tfWkQ46W7u7umsw1VtJcv7Vbe9pYe23Wvn79+qQjSNKY6ejoGGoWHLR3715eeOGFhBJJOp4TuSThNWBK9fcMNguONDYF8EIkSZIkSYcolUrDju3atYu/+Iu/SCCNpBNxIg2Dp4CPA4QQPgA8VzW2DvhwCGFiCOEcoBX4xYinlCRJknRaa25uflvHJSXvRBoGDwF7QwhPA/8F+P0QwpdCCEtijC8B3wJ+DKwBOmKMe0cvriRJkqTTUaFQIJvNHnIsm81SKBQSSiTpeI67h0GMsR+45bDDG6vG7wLuGuFckiRJksaRfD4PDOxlUCqVaG5uplAoDB2XVHtOZNNDSZIkSTpl+XyefD5f0xvSSnrLiVySIEmSJEmSUsaGgSRJkiRJGsaGgSRJkiRJGsaGgSRJkiRJGsaGgSRJkiRJGsaGgSRJkiRJGsaGgSRJkiRJGsaGgSRJkiRJGmZC0gEkJSfGyN/8zd9QV1fHJZdcwrx584543uOPP05jYyOXXXbZGCeUJEmSlBQbBlJKHThwgB/84AfcfPPNnHnmmaxcuZIQApMnTx46Z8+ePXzve9/jlVdeobGxMcG0kiRpvDrRDzAkjT0vSZBSaseOHTQ0NDBp0iTq6+u54IIL6OnpOeScffv2sWDBAi6++OKEUkqSpPHs4AcYN9xwA5/97Gf5+c9/zhtvvJF0LEmDbBhIKVEsFmlpaWH27Nm0tLTwyCOPMHHixKHxs846i97e3kO+59xzz2XatGljHVWSJKXEiXyAISk5NgykFCgWi7S3t9PT08OVV17JlVdeyaZNm9i8efPQOb29vYc0ECRJkkbayXyAISk57mEgpUBHRwflchmANWvWAFBXV8ftt9/Om2++yZlnnkmpVOKKK65IMqYkHVUIoQ74c2Au0At8Lsa4qWr8ZmAZ0AfcEWNcnUhQSUd18AOMcrnMRz/6UZqbm9m0aRPnnXfe0Dl+gCHVFhsGUgqUSqVhx/r7+3n00UeZNWsWlUqFSy65hKlTp/LrX/+adevWsXjx4gSSStJRXQNMjDFeHkL4APBN4LcBQgjvBm4FLgMmAj8JITwRY/RjSqmG+AGGdPqxYSClQHNz8xGvB9y7dy8333zzIcfe+c53DmsWLFy4cDTjSdKJ+BDwOECM8achhOr7vM4HnhpsEPSGEDYBFwM/O/xJuru7xyLr27J3796azDVW0lx/2mo/1gcYuVwOgJaWFrZu3crWrVvHOt6YSdvrXs3aT7/abRhIKVAoFIaWAB6UzWYpFAoJppKkt2UqsLvq8YEQwoQYY98Rxl4HzjnSk7S2to5ewpPU3d1dk7nGSprrT1vtx/oA49Zbb00gUTLS9rpXs/barH39+vVHHXPTQykF8vk8nZ2d5HI5MpkMuVyOzs5O8vl80tEk6US9Bkypelw32Cw40tgUYNdYBZN0YgqFAtls9pBjfoAh1TYbBlJK5PN5tmzZwoYNG9iyZYvNAkmnm6eAjwMM7mHwXNXYOuDDIYSJIYRzgFbgF2MfUdKx+AGGdPrxkgRJknQ6eAj4WAjhaSAD3BRC+BKwKcb4/RDCt4AfM/BhSEeMcW+CWSUdRT6fJ5/P1/TybElvsWEgSZJqXoyxH7jlsMMbq8bvAu4a01CSJI1zXpIgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGsWEgSZIkSZKGyVQqlVH/Q9avXz/6f4gkSaehefPmZZLOkBbORyRJOrKjzUfGpGEgSZIkSZJOL16SIEmSJEmShrFhIEmSJEmShrFhIEmSJEmShpmQdICRFEKoA/4cmAv0Ap+LMW6qGv/XwL8EXgP+Q4xxdQjhQuBeIAP0AO0xxnLV8z0KPBxjvHNMizkJI1l/COG3gH8zeHw98IUYY81ueDHCtX8ZuB7oB/7vGONDY1vNyQkhvB/4kxjjwsOOfxL4I6APWBljvCuEMAn4/4B3Aa8D/yrG+OsjnTuWNZysEar9XwK3D577HPD5GGP/GJZxUkai9qrv6QRejTF+Zazyn4oRet1/E/jPDPweeAm4Ica4dwzL0DiU5vlImuci4HwEnI/gfGThYcedj5zm85HxtsLgGmBijPFy4CvANw8OhBDmMPBL9wPAPwP+XQghC/xH4M4Y44eBJ4EvVT3fHcC5YxN9RIxI/SGEKYPHPxFjfD+wBWgcwzpOxkjV/g7gNuDywXOXj2URJyuE8AfAt4GJhx0/A/gvDNSyAGgPITQB/wfw3GDt/y/wtWOcW9NGqPZJDPx9vzLG+EHgHOATY1fFyRmJ2qu+ZxkwZ4yin7IRet0zwF3ATTHGDwGPA7mxq0LjWJrnI2mei4DzEecjzkeqjzsfGQfzkfHWMDj4AybG+FPgsqqxVuDJGOPewW7N/w9cDPwG8NjgOU8NPgchhE8z0NF9fGyij4iRqv8KBjqa3wwh/BjYXt31q1EjVfseBrr7Zw/+r+Y7uoP+EfidIxxvBTbFGHfGGPcBPwE+QtXPi4GfwdXHOLfWjUTtvcAVBz/NY2D1VU10dY9jJGonhHAF8H7gL0c98cgZidr/KfAK8PshhP8JNMQY46gnVxqkeT6S5rkIOB9xPjKc8xHnI6f1fGS8NQymArurHh8IIRy87OI54CMhhCkhhPMYeCM6G/hfwJLBc5YAZ4cQLmKgA/xHYxN7xIxI/Qx08K8E/jXwW8DtIYR/Ogb5T8VI1Q7wAvAPwM+Bb4128JEQY/wrYP8Rhg7/ubzOQLe6+viRjlUfr2kjUXuMsT/GuB0ghPB/ApOBJ0Yt9AgZidpDCOczsOT3i6MYdcSN0H/zjQz8PvgzBt6wrwohfHS0MitV0jwfSfNcBJyPOB8ZzvnIW5yPnIbzkfHWMHgNmFL1uC7G2AcQY+xm4EV4fPD//xbYAXwZWBJCeBKoDB67EXgvsAb4LANLw/752JRwSkaq/leAn8UYX4oxvgH8DXDJWBVxkkaq9t8CzgcuBJqBa0II88eohtFw+M9lCrDrsONHOlZ9/HT1dmonhFAXQvhPwMeAf1Hr18kex9up/XcZeKP6awaWz14fQvjsmCUdeW+n9lcY6P53xxj3M/A7ovrTQOlkpXk+kua5CDgfORrnI29xPuJ85LSaj4y3hsFTwMcBQggfYKCTy+DjdwJTBq8HugW4APgFA38Z/3Bwk4oDwBMxxj+IMb5/8Ng9wH+OMZ4OSwFHpH4GOtkXhRAaB7viH2Cgw13LRqr2ncCbQO/gcsFdwDvGrowR1w3MDCE0hBDOZGAp1Fqqfl4MTEp+fIxzT1dvp3YYWP42Ebimaing6eqEa48xfivGOG/w78H/A9wfY7wngcwj5e287r8EJocQZgwe/zCwYYzzanxK83wkzXMRcD5yNM5HnI84HzlN5yPj6i4JwEPAx0IITzOww+RNIYQvAZuAR4DWEMLPgH3A/xVjPBBCiEAxhNDLwAvzhYSyj4QRqT/GuD+E8FXgB4PP+99jjL8Y82renpGs/WrgpyGEfgauN6r5pWCHCyFcD0yOMXYO/hx+wECDcGWMcWsI4S+Ae0MIP2HgZ3L9YO3Dzk2qhpN1MrWHEN4HtDHwS3tNCAHgv8bTZEfqg06m9gTjjqiT/G9+XwihDbg/DGw49HSM8dHEitB4kub5SJrnIuB85BDOR5yPOB85/ecjmUrldF7lIkmSJEmSRsN4uyRBkiRJkiSNABsGkiRJkiRpGBsGkiRJkiRpGBsGkiRJkiRpGBsGkiQtUclAAAAAHUlEQVRJkiRpGBsGkiRJkiRpGBsGkiRJkiRpmP8N7NzWCfOQjiYAAAAASUVORK5CYII=\n",
       "text/plain": [
        "
    "
       ]
@@ -712,23 +667,8 @@
     }
    ],
    "source": [
-    "to_str1 = lambda x: \"{:.1f}\".format(x)\n",
-    "to_str2 = lambda x: \"{:d}\".format(x)\n",
-    "\n",
-    "fig, axarr = plt.subplots(ncols=2, figsize=[18, 8])\n",
-    "\n",
-    "for ax, dataset, to_str, title, b in zip(axarr,\n",
-    "                                         [data.y, signed_rank(data.y)],\n",
-    "                                         [to_str1, to_str1],\n",
-    "                                         [\"$t$-test\", \"Wilcoxon\"],\n",
-    "                                         [intercept, intercept_wilcoxon]):\n",
-    "    ax.set_title(title)\n",
-    "    ax.scatter(np.ones(50), dataset, color=\"k\")\n",
-    "    annotations = dataset.apply(to_str)\n",
-    "    for i, annot in enumerate(annotations):\n",
-    "        ax.annotate(annot, (1, dataset[i]), color=\"grey\")\n",
-    "    ax.axhline(a, color=\"b\", label=r\"$\\beta_0$ (Intercept)\")\n",
-    "    ax.legend(fontsize=\"large\")"
+    "plots.ttest_wilcoxon_plot(correlated_data, intercept, intercept_wilcoxon)\n",
+    "plt.show()"
    ]
   },
   {
@@ -742,7 +682,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 17,
+   "execution_count": 16,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -752,10 +692,8 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 18,
-   "metadata": {
-    "scrolled": true
-   },
+   "execution_count": 17,
+   "metadata": {},
    "outputs": [
     {
      "data": {
@@ -778,10 +716,9 @@
        "  \n",
        "    \n",
        "      \n",
-       "      slope\n",
+       "      value\n",
        "      p-values\n",
        "      t-values\n",
-       "      df\n",
        "      0.025 CI\n",
        "      0.975 CI\n",
        "    \n",
@@ -790,51 +727,39 @@
        "    \n",
        "      scipy.stats.ttest_1samp\n",
        "      NaN\n",
-       "      0.016092\n",
-       "      2.493053\n",
-       "      NaN\n",
+       "      0.882318\n",
+       "      0.148805\n",
        "      NaN\n",
        "      NaN\n",
        "    \n",
        "    \n",
        "      smf.ols (y ~ 1)\n",
-       "      0.369656\n",
-       "      0.016092\n",
-       "      2.493053\n",
-       "      49.0\n",
-       "      0.071687\n",
-       "      0.667624\n",
+       "      0.019429\n",
+       "      0.882318\n",
+       "      0.148805\n",
+       "      -0.242953\n",
+       "      0.281811\n",
        "    \n",
        "  \n",
        "\n",
        "
    "
       ],
       "text/plain": [
-       "                            slope  p-values  t-values    df  0.025 CI  \\\n",
-       "scipy.stats.ttest_1samp       NaN  0.016092  2.493053   NaN       NaN   \n",
-       "smf.ols (y ~ 1)          0.369656  0.016092  2.493053  49.0  0.071687   \n",
-       "\n",
-       "                         0.975 CI  \n",
-       "scipy.stats.ttest_1samp       NaN  \n",
-       "smf.ols (y ~ 1)          0.667624  "
+       "                            value  p-values  t-values  0.025 CI  0.975 CI\n",
+       "scipy.stats.ttest_1samp       NaN  0.882318  0.148805       NaN       NaN\n",
+       "smf.ols (y ~ 1)          0.019429  0.882318  0.148805 -0.242953  0.281811"
       ]
      },
-     "execution_count": 18,
+     "execution_count": 17,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Tabulate and display\n",
-    "df = pd.DataFrame(index=[\"scipy.stats.ttest_1samp\", \"smf.ols (y ~ 1)\"])\n",
-    "df[\"slope\"] = [None, res.params.Intercept]\n",
-    "df[\"p-values\"] = [p, res.pvalues.Intercept]\n",
-    "df[\"t-values\"] = [t, res.tvalues.Intercept]\n",
-    "df[\"df\"] = [None, res.df_resid]\n",
-    "df[\"0.025 CI\"] = [None, res.conf_int().loc[\"Intercept\", 0]]\n",
-    "df[\"0.975 CI\"] = [None, res.conf_int().loc[\"Intercept\", 1]]\n",
-    "\n",
-    "df"
+    "utils.tabulate_results([None, p, t, None, None],\n",
+    "                       res,\n",
+    "                       [\"scipy.stats.ttest_1samp\", \"smf.ols (y ~ 1)\"],\n",
+    "                       x=False)"
    ]
   },
   {
@@ -848,7 +773,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 19,
+   "execution_count": 18,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -861,7 +786,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 19,
    "metadata": {},
    "outputs": [
     {
@@ -885,10 +810,9 @@
        "  \n",
        "    \n",
        "      \n",
-       "      slope\n",
+       "      value\n",
        "      p-values\n",
        "      t-values\n",
-       "      df\n",
        "      0.025 CI\n",
        "      0.975 CI\n",
        "    \n",
@@ -897,51 +821,39 @@
        "    \n",
        "      scipy.stats.wilcoxon\n",
        "      NaN\n",
-       "      0.017335\n",
-       "      NaN\n",
+       "      0.942284\n",
        "      NaN\n",
        "      NaN\n",
        "      NaN\n",
        "    \n",
        "    \n",
        "      smf.ols (y ~ 1, signed rank)\n",
-       "      7.62\n",
-       "      0.057262\n",
-       "      1.947136\n",
-       "      49.0\n",
-       "      -0.244352\n",
-       "      15.484352\n",
+       "      -2.78\n",
+       "      0.494895\n",
+       "      -0.687683\n",
+       "      -10.903825\n",
+       "      5.343825\n",
        "    \n",
        "  \n",
        "\n",
        "
    "
       ],
       "text/plain": [
-       "                              slope  p-values  t-values    df  0.025 CI  \\\n",
-       "scipy.stats.wilcoxon            NaN  0.017335       NaN   NaN       NaN   \n",
-       "smf.ols (y ~ 1, signed rank)   7.62  0.057262  1.947136  49.0 -0.244352   \n",
-       "\n",
-       "                               0.975 CI  \n",
-       "scipy.stats.wilcoxon                NaN  \n",
-       "smf.ols (y ~ 1, signed rank)  15.484352  "
+       "                              value  p-values  t-values   0.025 CI  0.975 CI\n",
+       "scipy.stats.wilcoxon            NaN  0.942284       NaN        NaN       NaN\n",
+       "smf.ols (y ~ 1, signed rank)  -2.78  0.494895 -0.687683 -10.903825  5.343825"
       ]
      },
-     "execution_count": 20,
+     "execution_count": 19,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Tabulate and display\n",
-    "df = pd.DataFrame(index=[\"scipy.stats.wilcoxon\", \"smf.ols (y ~ 1, signed rank)\"])\n",
-    "df[\"slope\"] = [None, res.params.Intercept]\n",
-    "df[\"p-values\"] = [p, res.pvalues.Intercept]\n",
-    "df[\"t-values\"] = [None, res.tvalues.Intercept]\n",
-    "df[\"df\"] = [None, res.df_resid]\n",
-    "df[\"0.025 CI\"] = [None, res.conf_int().loc[\"Intercept\", 0]]\n",
-    "df[\"0.975 CI\"] = [None, res.conf_int().loc[\"Intercept\", 1]]\n",
-    "\n",
-    "df"
+    "utils.tabulate_results([None, p, None, None, None],\n",
+    "                       res,\n",
+    "                       [\"scipy.stats.wilcoxon\", \"smf.ols (y ~ 1, signed rank)\"],\n",
+    "                       x=False)"
    ]
   },
   {
@@ -961,7 +873,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 20,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -977,15 +889,6 @@
     "$\\text{signed_rank}(y_2-y_1) = \\beta_0 \\qquad \\mathcal{H}_0: \\beta_0 = 0$"
    ]
   },
-  {
-   "cell_type": "code",
-   "execution_count": 22,
-   "metadata": {},
-   "outputs": [],
-   "source": [
-    "# TODO"
-   ]
-  },
   {
    "cell_type": "markdown",
    "metadata": {},
@@ -995,7 +898,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 23,
+   "execution_count": 21,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1005,7 +908,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 24,
+   "execution_count": 22,
    "metadata": {},
    "outputs": [
     {
@@ -1029,10 +932,9 @@
        "  \n",
        "    \n",
        "      \n",
-       "      slope\n",
+       "      value\n",
        "      p-values\n",
        "      t-values\n",
-       "      df\n",
        "      0.025 CI\n",
        "      0.975 CI\n",
        "    \n",
@@ -1041,47 +943,39 @@
        "    \n",
        "      scipy.stats.ttest_ind\n",
        "      NaN\n",
-       "      0.699144\n",
-       "      -0.387612\n",
-       "      NaN\n",
+       "      0.119175\n",
+       "      -1.571994\n",
        "      NaN\n",
        "      NaN\n",
        "    \n",
        "    \n",
        "      smf.ols (y_sub_y2 ~ 1)\n",
-       "      -0.079916\n",
-       "      0.702639\n",
-       "      -0.384001\n",
-       "      49.0\n",
-       "      -0.498137\n",
-       "      0.338305\n",
+       "      -0.278406\n",
+       "      0.075029\n",
+       "      -1.818975\n",
+       "      -0.585985\n",
+       "      0.029173\n",
        "    \n",
        "  \n",
        "\n",
        "
    "
       ],
       "text/plain": [
-       "                           slope  p-values  t-values    df  0.025 CI  0.975 CI\n",
-       "scipy.stats.ttest_ind        NaN  0.699144 -0.387612   NaN       NaN       NaN\n",
-       "smf.ols (y_sub_y2 ~ 1) -0.079916  0.702639 -0.384001  49.0 -0.498137  0.338305"
+       "                           value  p-values  t-values  0.025 CI  0.975 CI\n",
+       "scipy.stats.ttest_ind        NaN  0.119175 -1.571994       NaN       NaN\n",
+       "smf.ols (y_sub_y2 ~ 1) -0.278406  0.075029 -1.818975 -0.585985  0.029173"
       ]
      },
-     "execution_count": 24,
+     "execution_count": 22,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Tabulate and display\n",
-    "df = pd.DataFrame(index=[\"scipy.stats.ttest_ind\", \"smf.ols (y_sub_y2 ~ 1)\"])\n",
-    "df[\"slope\"] = [None, res.params.Intercept]\n",
-    "df[\"p-values\"] = [p, res.pvalues.Intercept]\n",
-    "df[\"t-values\"] = [t, res.tvalues.Intercept]\n",
-    "df[\"df\"] = [None, res.df_resid]\n",
-    "df[\"0.025 CI\"] = [None, res.conf_int().loc[\"Intercept\", 0]]\n",
-    "df[\"0.975 CI\"] = [None, res.conf_int().loc[\"Intercept\", 1]]\n",
-    "\n",
-    "df"
+    "utils.tabulate_results([None, p, t, None, None],\n",
+    "                       res,\n",
+    "                       [\"scipy.stats.ttest_ind\", \"smf.ols (y_sub_y2 ~ 1)\"],\n",
+    "                       x=False)"
    ]
   },
   {
@@ -1095,7 +989,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 25,
+   "execution_count": 23,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1106,7 +1000,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 26,
+   "execution_count": 24,
    "metadata": {},
    "outputs": [
     {
@@ -1130,10 +1024,9 @@
        "  \n",
        "    \n",
        "      \n",
-       "      slope\n",
+       "      value\n",
        "      p-values\n",
        "      t-values\n",
-       "      df\n",
        "      0.025 CI\n",
        "      0.975 CI\n",
        "    \n",
@@ -1142,60 +1035,47 @@
        "    \n",
        "      scipy.stats.wilcoxon\n",
        "      NaN\n",
-       "      0.881060\n",
-       "      NaN\n",
+       "      0.071808\n",
        "      NaN\n",
        "      NaN\n",
        "      NaN\n",
        "    \n",
        "    \n",
        "      smf.ols (y_sub_y2 ~ 1)\n",
-       "      3.22\n",
-       "      0.428812\n",
-       "      0.797842\n",
-       "      49.0\n",
-       "      -4.890423\n",
-       "      11.330423\n",
+       "      -5.18\n",
+       "      0.200729\n",
+       "      -1.296931\n",
+       "      -13.206335\n",
+       "      2.846335\n",
        "    \n",
        "  \n",
        "\n",
        "
    "
       ],
       "text/plain": [
-       "                        slope  p-values  t-values    df  0.025 CI   0.975 CI\n",
-       "scipy.stats.wilcoxon      NaN  0.881060       NaN   NaN       NaN        NaN\n",
-       "smf.ols (y_sub_y2 ~ 1)   3.22  0.428812  0.797842  49.0 -4.890423  11.330423"
+       "                        value  p-values  t-values   0.025 CI  0.975 CI\n",
+       "scipy.stats.wilcoxon      NaN  0.071808       NaN        NaN       NaN\n",
+       "smf.ols (y_sub_y2 ~ 1)  -5.18  0.200729 -1.296931 -13.206335  2.846335"
       ]
      },
-     "execution_count": 26,
+     "execution_count": 24,
      "metadata": {},
      "output_type": "execute_result"
     }
    ],
    "source": [
-    "# Tabulate and display\n",
-    "df = pd.DataFrame(index=[\"scipy.stats.wilcoxon\", \"smf.ols (y_sub_y2 ~ 1)\"])\n",
-    "df[\"slope\"] = [None, res.params.Intercept]\n",
-    "df[\"p-values\"] = [p, res.pvalues.Intercept]\n",
-    "df[\"t-values\"] = [None, res.tvalues.Intercept]\n",
-    "df[\"df\"] = [None, res.df_resid]\n",
-    "df[\"0.025 CI\"] = [None, res.conf_int().loc[\"Intercept\", 0]]\n",
-    "df[\"0.975 CI\"] = [None, res.conf_int().loc[\"Intercept\", 1]]\n",
-    "\n",
-    "df"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "For large sample sizes (N >> 100), this approaches the **sign test** to a reasonable degree, but this approximation is too inaccurate to flesh out here."
+    "utils.tabulate_results([None, p, None, None, None],\n",
+    "                       res,\n",
+    "                       [\"scipy.stats.wilcoxon\", \"smf.ols (y_sub_y2 ~ 1)\"],\n",
+    "                       x=False)"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
+    "For large sample sizes (N >> 100), this approaches the **sign test** to a reasonable degree, but this approximation is too inaccurate to flesh out here.\n",
+    "\n",
     "# 5 Two means\n",
     "\n",
     "## 5.1 Independent t-test and Mann-Whitney U\n",
@@ -1225,7 +1105,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 27,
+   "execution_count": 25,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1257,7 +1137,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 28,
+   "execution_count": 26,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -1273,12 +1153,30 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 29,
+   "execution_count": 27,
    "metadata": {},
    "outputs": [],
    "source": [
     "# TODO"
    ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## 5.2 Welch’s t-test\n",
+    "\n",
+    "This is identical to the (Student's) [independent t-test](#t2) above except that Student's assumes identical variances and **Welch's t-test** does not. So the linear model is the same and the trick is in the variances, which I won't go further into here."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "t, p = scipy.stats.ttest_ind(data.y, data.y2, equal_var=False)"
+   ]
   }
  ],
  "metadata": {
diff --git a/utils.py b/utils.py
index a5cd0ac..52da92a 100644
--- a/utils.py
+++ b/utils.py
@@ -2,6 +2,61 @@
 
 import re
 import json
+import numpy as np
+import pandas as pd
+
+
+def signed_rank(x, axis=-1):
+    return np.sign(x) * np.argsort(x, axis=axis)
+
+
+def format_decimals_factory(num_decimals=1):
+    return lambda x: "{1:.{0}f}".format(num_decimals, x)
+
+
+def tabulate_results(test_values, ols_results, names, x=True):
+    """
+    Tabulates results of statistical tests and equivalent linear regressions to
+    demonstrate that the two methods are in fact equivalent.
+
+    Parameters
+    ----------
+    test_values : list
+        List of values from the scipy statistical test to display.
+    ols_results : statsmodels.RegressionResults or list thereof
+        Result object(s) of equivalent linear regression to display.
+    names : list
+        List of strings to display.
+    x : bool
+        If True, display `x` coefficient for parameters, p and t values.
+        Otherwise, display `Intercept` coefficient.
+
+    Returns
+    -------
+    table : pd.DataFrame
+    """
+    # There may be only one OLS result. If so, wrap it up as a single list.
+    if not isinstance(ols_results, list):
+        ols_results = [ols_results]
+
+    # Assert shapes
+    assert len(test_values) == 5
+    assert len(names) == len(ols_results) + 1
+
+    # Construct and return table
+    table = pd.DataFrame(index=names)
+    coeff = "x" if x else "Intercept"
+    table["value"] = [test_values[0]] + [res.params[coeff] for res in ols_results]
+    table["p-values"] = [test_values[1]] + [res.pvalues[coeff] for res in ols_results]
+    table["t-values"] = [test_values[2]] + [res.tvalues[coeff] for res in ols_results]
+    table["0.025 CI"] = [test_values[3]] + [
+        res.conf_int().loc[coeff, 0] for res in ols_results
+    ]
+    table["0.975 CI"] = [test_values[4]] + [
+        res.conf_int().loc[coeff, 1] for res in ols_results
+    ]
+
+    return table
 
 
 def generate_toc(notebook="tests-as-linear.ipynb"):
@@ -25,7 +80,7 @@ def generate_toc(notebook="tests-as-linear.ipynb"):
     with open(notebook, "r") as f:
         cells = json.load(f)["cells"]
 
-    items = ["# Table of contents\n"]
+    items = ["# Table of contents"]
     for cell in cells:
         if cell["cell_type"] == "markdown":
             for line in cell["source"]:
@@ -39,11 +94,8 @@ def generate_toc(notebook="tests-as-linear.ipynb"):
                         + line.strip(" #\n")
                         + "](#"
                         + link
-                        + ")\n"
+                        + ")"
                     )
 
-    toc = ""
-    for item in items:
-        toc += item
-
+    toc = "\n".join(items)
     return toc