diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 13f4987..2fefab3 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -1,4 +1,4 @@ -name: Release +name: Release package on: # should work diff --git a/.gitignore b/.gitignore index 1c97a43..5da3ca4 100644 --- a/.gitignore +++ b/.gitignore @@ -111,4 +111,7 @@ GitHub.sublime-settings *.png .DS_Store !data.csv -!example.png \ No newline at end of file +!example.png +!cmp.html +!time_window_corrected.csv +!group_cluster.csv \ No newline at end of file diff --git a/Dockerfile b/Dockerfile index 3e0c687..379c6a8 100644 --- a/Dockerfile +++ b/Dockerfile @@ -4,7 +4,7 @@ # If you need more help, visit the Dockerfile reference guide at # https://docs.docker.com/engine/reference/builder/ -ARG PYTHON_VERSION=3.12.3 +ARG PYTHON_VERSION=3.11 FROM python:${PYTHON_VERSION}-slim as base # Prevents Python from writing pyc files. @@ -36,8 +36,12 @@ RUN adduser \ # Leverage a bind mount to requirements.txt to avoid having to copy them into # into this layer. RUN --mount=type=cache,target=/root/.cache/pip \ - --mount=type=bind,source=requirements.txt,target=requirements.txt \ - python -m pip install -r requirements.txt + --mount=type=bind,source=pyproject.toml,target=pyproject.toml \ + --mount=type=bind,source=poetry.lock,target=poetry.lock \ + python -m pip install poetry && \ + poetry config virtualenvs.create false && \ + poetry install --only main --no-interaction --no-ansi && \ + rm -rf $POETRY_CACHE_DIR # Switch to the non-privileged user to run the application. USER appuser diff --git a/Makefile b/Makefile index 5522a60..691287b 100644 --- a/Makefile +++ b/Makefile @@ -36,6 +36,7 @@ docker-run: .PHONY: rm-git-cache +rm-git-cache: ## Remove git cached files rm-git-cache: @echo "Removing git cached files" git add . @@ -43,6 +44,7 @@ rm-git-cache: git add . .PHONY: setup +setup: ## Setup the project setup: @if [ ! -d "${VENV}" ]; then \ echo "Creating venv"; \ diff --git a/README.md b/README.md index ab7d2c2..b543cd0 100644 --- a/README.md +++ b/README.md @@ -1,9 +1,13 @@ # Contextual Matrix Profile Calculation Tool -The Matrix Profile has the potential to revolutionize time series data mining because of its generality, versatility, -simplicity and scalability. In particular it has implications for time series motif discovery, time series joins, -shapelet discovery (classification), density estimation, semantic segmentation, visualization, rule discovery, -clustering etc. +Matrix Profile is an algorithm capable to discover motifs and discords in time series data. It is a powerful tool that +by calculating the (z-normalized) Euclidean distance between any subsequence within a time series and its nearest +neighbor it is able to provide insights on potential anomalies and/or repetitive patterns. In the field of building +energy management it can be employed to detect anomalies in electrical load timeseries. + +This tool is a Python implementation of the Matrix Profile algorithm that employs contextual information (such as +external air temperature) to identify abnormal pattens in electrical load subsequences that start in predefined sub +daily time windows, as shown in the following figure. ![](./docs/example.png) @@ -20,7 +24,7 @@ clustering etc. ## Usage -The tool comes with a cli that helps you to execute the script with the desired commands +The tool comes with a CLI that helps you to execute the script with the desired commands ```console $ python -m src.cmp.main -h @@ -39,7 +43,7 @@ options: The arguments to pass to the script are the following: * `input_file`: The input dataset via an HTTP URL. The tool should then download the dataset from that URL; since it's a - presigned URL, the tool would not need to deal with authentication—it can just download the dataset directly. + pre-signed URL, the tool would not need to deal with authentication—it can just download the dataset directly. * `variable_name`: The variable name to be used for the analysis (i.e., the column of the csv that contains the electrical load under analysis). * `output_file`: The local path to the output HTML report. The platform would then get that HTML report and upload it to @@ -47,12 +51,33 @@ The arguments to pass to the script are the following: storage service for the user to review later. You can run the main script through the console using either local files or download data from an external url. This -repository comes with a sample dataset (data.csv) that you can use to generate a report and you can pass the local path +repository comes with a sample dataset ([data.csv](.src/cmp/data/data.csv)) that you can use to generate a report and +you can pass the local path as `input_file` argument as follows: ### Data format -todo +The tool requires the user to provide a csv file as input that contains electrical power timeseries for a specific +building, meter or energy system (e.g., whole building electrical power timeseries). The `csv` is a wide table format as +follows: + +```csv +timestamp,column_1,temp +2019-01-01 00:00:00,116.4,-0.6 +2019-01-01 00:15:00,125.6,-0.9 +2019-01-01 00:30:00,119.2,-1.2 +``` + +The csv must have the following columns: + +- `timestamp` [case sensitive]: The timestamp of the observation in the format `YYYY-MM-DD HH:MM:SS`. This column is + supposed to be in + UTC timezone string format. It will be internally transformed by the tool into the index of the dataframe. +- `temp` [case sensitive]: Contains the external air temperature in Celsius degrees. This column is required to perform + thermal sensitive + analysis on the electrical load. +- `column_1`: Then the dataframe may have `N` arbitrary columns that refers to electrical load time series. The user has + to specify the column name that refers to the electrical load time series in the `variable_name` argument. ### Run locally @@ -62,6 +87,7 @@ Create virtual environment and activate it and install dependencies: ```bash make setup ``` + - Linux: ```bash python3 -m venv .venv @@ -134,44 +160,6 @@ Run the docker image with the same arguments as before At the end of the execution you can find the results in the [`results`](src/cmp/results) folder inside the docker container. -## Additional Information - -``` -# 2) User Defined Context -# We want to find all the subsequences that start from 00:00 to 02:00 (2 hours) and covers the whole day -# In order to avoid overlapping we define the window length as the whole day of -# observation minus the context length. - -# - Beginning of the context 00:00 AM [hours] -context_start = 17 - -# - End of the context 02:00 AM [hours] -context_end = 19 - -# - Context time window length 2 [hours] -m_context = context_end - context_start # 2 - -# - Time window length [observations] -# m = 96 [observations] - 4 [observation/hour] * 2 [hours] = 88 [observations] = 22 [hours] -# m = obs_per_day - obs_per_hour * m_context -m = 20 # with guess - -# Context Definition: -# example FROM 00:00 to 02:00 -# - m_context = 2 [hours] -# - obs_per_hour = 4 [observations/hour] -# - context_start = 0 [hours] -# - context_end = context_start + m_context = 0 [hours] + 2 [hours] = 2 [hours] -contexts = GeneralStaticManager([ - range( - # FROM [observations] = x * 96 [observations] + 0 [hour] * 4 [observation/hour] - (x * obs_per_day) + context_start * obs_per_hour, - # TO [observations] = x * 96 [observations] + (0 [hour] + 2 [hour]) * 4 [observation/hour] - (x * obs_per_day) + (context_start + m_context) * obs_per_hour) - for x in range(len(data) // obs_per_day) -]) -``` - ## Cite You can cite this work by using the following reference or either though [this Bibtex file](./docs/ref.bib) or the @@ -183,7 +171,12 @@ following plain text citation ## Contributors -- [Roberto Chiosa](https://github.com/RobertoChiosa) +- Author [Roberto Chiosa](https://github.com/RobertoChiosa) + +## References + +- Series Distance Matrix repository (https://github.com/predict-idlab/seriesdistancematrix) +- Stumpy Package (https://stumpy.readthedocs.io/en/latest/) ## License diff --git a/RELEASE.md b/RELEASE.md index a8148e6..640b93b 100644 --- a/RELEASE.md +++ b/RELEASE.md @@ -1,3 +1,5 @@ ### Features: -- Added command line interface for the tool \ No newline at end of file +- Fixed csv path issues +- Documentation updates +- Docker run support \ No newline at end of file diff --git a/poetry.lock b/poetry.lock index f1b0dc5..a2c9e52 100644 --- a/poetry.lock +++ b/poetry.lock @@ -11,6 +11,116 @@ files = [ {file = "argparse-1.4.0.tar.gz", hash = "sha256:62b089a55be1d8949cd2bc7e0df0bddb9e028faefc8c32038cc84862aefdd6e4"}, ] +[[package]] +name = "certifi" +version = "2024.7.4" +description = "Python package for providing Mozilla's CA Bundle." +optional = false +python-versions = ">=3.6" +files = [ + {file = "certifi-2024.7.4-py3-none-any.whl", hash = "sha256:c198e21b1289c2ab85ee4e67bb4b4ef3ead0892059901a8d5b622f24a1101e90"}, + {file = "certifi-2024.7.4.tar.gz", hash = "sha256:5a1e7645bc0ec61a09e26c36f6106dd4cf40c6db3a1fb6352b0244e7fb057c7b"}, +] + +[[package]] +name = "charset-normalizer" +version = "3.3.2" +description = "The Real First Universal Charset Detector. Open, modern and actively maintained alternative to Chardet." +optional = false +python-versions = ">=3.7.0" +files = [ + {file = "charset-normalizer-3.3.2.tar.gz", hash = "sha256:f30c3cb33b24454a82faecaf01b19c18562b1e89558fb6c56de4d9118a032fd5"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_universal2.whl", hash = "sha256:25baf083bf6f6b341f4121c2f3c548875ee6f5339300e08be3f2b2ba1721cdd3"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_10_9_x86_64.whl", hash = "sha256:06435b539f889b1f6f4ac1758871aae42dc3a8c0e24ac9e60c2384973ad73027"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-macosx_11_0_arm64.whl", hash = "sha256:9063e24fdb1e498ab71cb7419e24622516c4a04476b17a2dab57e8baa30d6e03"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:6897af51655e3691ff853668779c7bad41579facacf5fd7253b0133308cf000d"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1d3193f4a680c64b4b6a9115943538edb896edc190f0b222e73761716519268e"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:cd70574b12bb8a4d2aaa0094515df2463cb429d8536cfb6c7ce983246983e5a6"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8465322196c8b4d7ab6d1e049e4c5cb460d0394da4a27d23cc242fbf0034b6b5"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:a9a8e9031d613fd2009c182b69c7b2c1ef8239a0efb1df3f7c8da66d5dd3d537"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_aarch64.whl", hash = "sha256:beb58fe5cdb101e3a055192ac291b7a21e3b7ef4f67fa1d74e331a7f2124341c"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_i686.whl", hash = "sha256:e06ed3eb3218bc64786f7db41917d4e686cc4856944f53d5bdf83a6884432e12"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_ppc64le.whl", hash = "sha256:2e81c7b9c8979ce92ed306c249d46894776a909505d8f5a4ba55b14206e3222f"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_s390x.whl", hash = "sha256:572c3763a264ba47b3cf708a44ce965d98555f618ca42c926a9c1616d8f34269"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-musllinux_1_1_x86_64.whl", hash = "sha256:fd1abc0d89e30cc4e02e4064dc67fcc51bd941eb395c502aac3ec19fab46b519"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-win32.whl", hash = "sha256:3d47fa203a7bd9c5b6cee4736ee84ca03b8ef23193c0d1ca99b5089f72645c73"}, + {file = "charset_normalizer-3.3.2-cp310-cp310-win_amd64.whl", hash = "sha256:10955842570876604d404661fbccbc9c7e684caf432c09c715ec38fbae45ae09"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_universal2.whl", hash = "sha256:802fe99cca7457642125a8a88a084cef28ff0cf9407060f7b93dca5aa25480db"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_10_9_x86_64.whl", hash = "sha256:573f6eac48f4769d667c4442081b1794f52919e7edada77495aaed9236d13a96"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-macosx_11_0_arm64.whl", hash = "sha256:549a3a73da901d5bc3ce8d24e0600d1fa85524c10287f6004fbab87672bf3e1e"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:f27273b60488abe721a075bcca6d7f3964f9f6f067c8c4c605743023d7d3944f"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:1ceae2f17a9c33cb48e3263960dc5fc8005351ee19db217e9b1bb15d28c02574"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:65f6f63034100ead094b8744b3b97965785388f308a64cf8d7c34f2f2e5be0c4"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:753f10e867343b4511128c6ed8c82f7bec3bd026875576dfd88483c5c73b2fd8"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:4a78b2b446bd7c934f5dcedc588903fb2f5eec172f3d29e52a9096a43722adfc"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_aarch64.whl", hash = "sha256:e537484df0d8f426ce2afb2d0f8e1c3d0b114b83f8850e5f2fbea0e797bd82ae"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_i686.whl", hash = "sha256:eb6904c354526e758fda7167b33005998fb68c46fbc10e013ca97f21ca5c8887"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_ppc64le.whl", hash = "sha256:deb6be0ac38ece9ba87dea880e438f25ca3eddfac8b002a2ec3d9183a454e8ae"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_s390x.whl", hash = "sha256:4ab2fe47fae9e0f9dee8c04187ce5d09f48eabe611be8259444906793ab7cbce"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-musllinux_1_1_x86_64.whl", hash = "sha256:80402cd6ee291dcb72644d6eac93785fe2c8b9cb30893c1af5b8fdd753b9d40f"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-win32.whl", hash = "sha256:7cd13a2e3ddeed6913a65e66e94b51d80a041145a026c27e6bb76c31a853c6ab"}, + {file = "charset_normalizer-3.3.2-cp311-cp311-win_amd64.whl", hash = "sha256:663946639d296df6a2bb2aa51b60a2454ca1cb29835324c640dafb5ff2131a77"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_universal2.whl", hash = "sha256:0b2b64d2bb6d3fb9112bafa732def486049e63de9618b5843bcdd081d8144cd8"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_10_9_x86_64.whl", hash = "sha256:ddbb2551d7e0102e7252db79ba445cdab71b26640817ab1e3e3648dad515003b"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:55086ee1064215781fff39a1af09518bc9255b50d6333f2e4c74ca09fac6a8f6"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:8f4a014bc36d3c57402e2977dada34f9c12300af536839dc38c0beab8878f38a"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a10af20b82360ab00827f916a6058451b723b4e65030c5a18577c8b2de5b3389"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:8d756e44e94489e49571086ef83b2bb8ce311e730092d2c34ca8f7d925cb20aa"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:90d558489962fd4918143277a773316e56c72da56ec7aa3dc3dbbe20fdfed15b"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:6ac7ffc7ad6d040517be39eb591cac5ff87416c2537df6ba3cba3bae290c0fed"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:7ed9e526742851e8d5cc9e6cf41427dfc6068d4f5a3bb03659444b4cabf6bc26"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_i686.whl", hash = "sha256:8bdb58ff7ba23002a4c5808d608e4e6c687175724f54a5dade5fa8c67b604e4d"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_ppc64le.whl", hash = "sha256:6b3251890fff30ee142c44144871185dbe13b11bab478a88887a639655be1068"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_s390x.whl", hash = "sha256:b4a23f61ce87adf89be746c8a8974fe1c823c891d8f86eb218bb957c924bb143"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:efcb3f6676480691518c177e3b465bcddf57cea040302f9f4e6e191af91174d4"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-win32.whl", hash = "sha256:d965bba47ddeec8cd560687584e88cf699fd28f192ceb452d1d7ee807c5597b7"}, + {file = "charset_normalizer-3.3.2-cp312-cp312-win_amd64.whl", hash = "sha256:96b02a3dc4381e5494fad39be677abcb5e6634bf7b4fa83a6dd3112607547001"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-macosx_10_9_x86_64.whl", hash = "sha256:95f2a5796329323b8f0512e09dbb7a1860c46a39da62ecb2324f116fa8fdc85c"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c002b4ffc0be611f0d9da932eb0f704fe2602a9a949d1f738e4c34c75b0863d5"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:a981a536974bbc7a512cf44ed14938cf01030a99e9b3a06dd59578882f06f985"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:3287761bc4ee9e33561a7e058c72ac0938c4f57fe49a09eae428fd88aafe7bb6"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:42cb296636fcc8b0644486d15c12376cb9fa75443e00fb25de0b8602e64c1714"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:0a55554a2fa0d408816b3b5cedf0045f4b8e1a6065aec45849de2d6f3f8e9786"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_aarch64.whl", hash = "sha256:c083af607d2515612056a31f0a8d9e0fcb5876b7bfc0abad3ecd275bc4ebc2d5"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_i686.whl", hash = "sha256:87d1351268731db79e0f8e745d92493ee2841c974128ef629dc518b937d9194c"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_ppc64le.whl", hash = "sha256:bd8f7df7d12c2db9fab40bdd87a7c09b1530128315d047a086fa3ae3435cb3a8"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_s390x.whl", hash = "sha256:c180f51afb394e165eafe4ac2936a14bee3eb10debc9d9e4db8958fe36afe711"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-musllinux_1_1_x86_64.whl", hash = "sha256:8c622a5fe39a48f78944a87d4fb8a53ee07344641b0562c540d840748571b811"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-win32.whl", hash = "sha256:db364eca23f876da6f9e16c9da0df51aa4f104a972735574842618b8c6d999d4"}, + {file = "charset_normalizer-3.3.2-cp37-cp37m-win_amd64.whl", hash = "sha256:86216b5cee4b06df986d214f664305142d9c76df9b6512be2738aa72a2048f99"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_universal2.whl", hash = "sha256:6463effa3186ea09411d50efc7d85360b38d5f09b870c48e4600f63af490e56a"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_10_9_x86_64.whl", hash = "sha256:6c4caeef8fa63d06bd437cd4bdcf3ffefe6738fb1b25951440d80dc7df8c03ac"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-macosx_11_0_arm64.whl", hash = "sha256:37e55c8e51c236f95b033f6fb391d7d7970ba5fe7ff453dad675e88cf303377a"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:fb69256e180cb6c8a894fee62b3afebae785babc1ee98b81cdf68bbca1987f33"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:ae5f4161f18c61806f411a13b0310bea87f987c7d2ecdbdaad0e94eb2e404238"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:b2b0a0c0517616b6869869f8c581d4eb2dd83a4d79e0ebcb7d373ef9956aeb0a"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:45485e01ff4d3630ec0d9617310448a8702f70e9c01906b0d0118bdf9d124cf2"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:eb00ed941194665c332bf8e078baf037d6c35d7c4f3102ea2d4f16ca94a26dc8"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_aarch64.whl", hash = "sha256:2127566c664442652f024c837091890cb1942c30937add288223dc895793f898"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_i686.whl", hash = "sha256:a50aebfa173e157099939b17f18600f72f84eed3049e743b68ad15bd69b6bf99"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_ppc64le.whl", hash = "sha256:4d0d1650369165a14e14e1e47b372cfcb31d6ab44e6e33cb2d4e57265290044d"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_s390x.whl", hash = "sha256:923c0c831b7cfcb071580d3f46c4baf50f174be571576556269530f4bbd79d04"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-musllinux_1_1_x86_64.whl", hash = "sha256:06a81e93cd441c56a9b65d8e1d043daeb97a3d0856d177d5c90ba85acb3db087"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-win32.whl", hash = "sha256:6ef1d82a3af9d3eecdba2321dc1b3c238245d890843e040e41e470ffa64c3e25"}, + {file = "charset_normalizer-3.3.2-cp38-cp38-win_amd64.whl", hash = "sha256:eb8821e09e916165e160797a6c17edda0679379a4be5c716c260e836e122f54b"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_universal2.whl", hash = "sha256:c235ebd9baae02f1b77bcea61bce332cb4331dc3617d254df3323aa01ab47bd4"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_10_9_x86_64.whl", hash = "sha256:5b4c145409bef602a690e7cfad0a15a55c13320ff7a3ad7ca59c13bb8ba4d45d"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-macosx_11_0_arm64.whl", hash = "sha256:68d1f8a9e9e37c1223b656399be5d6b448dea850bed7d0f87a8311f1ff3dabb0"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:22afcb9f253dac0696b5a4be4a1c0f8762f8239e21b99680099abd9b2b1b2269"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e27ad930a842b4c5eb8ac0016b0a54f5aebbe679340c26101df33424142c143c"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:1f79682fbe303db92bc2b1136016a38a42e835d932bab5b3b1bfcfbf0640e519"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b261ccdec7821281dade748d088bb6e9b69e6d15b30652b74cbbac25e280b796"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-manylinux_2_5_i686.manylinux1_i686.manylinux_2_17_i686.manylinux2014_i686.whl", hash = "sha256:122c7fa62b130ed55f8f285bfd56d5f4b4a5b503609d181f9ad85e55c89f4185"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_aarch64.whl", hash = "sha256:d0eccceffcb53201b5bfebb52600a5fb483a20b61da9dbc885f8b103cbe7598c"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_i686.whl", hash = "sha256:9f96df6923e21816da7e0ad3fd47dd8f94b2a5ce594e00677c0013018b813458"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_ppc64le.whl", hash = "sha256:7f04c839ed0b6b98b1a7501a002144b76c18fb1c1850c8b98d458ac269e26ed2"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_s390x.whl", hash = "sha256:34d1c8da1e78d2e001f363791c98a272bb734000fcef47a491c1e3b0505657a8"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-musllinux_1_1_x86_64.whl", hash = "sha256:ff8fa367d09b717b2a17a052544193ad76cd49979c805768879cb63d9ca50561"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-win32.whl", hash = "sha256:aed38f6e4fb3f5d6bf81bfa990a07806be9d83cf7bacef998ab1a9bd660a581f"}, + {file = "charset_normalizer-3.3.2-cp39-cp39-win_amd64.whl", hash = "sha256:b01b88d45a6fcb69667cd6d2f7a9aeb4bf53760d7fc536bf679ec94fe9f3ff3d"}, + {file = "charset_normalizer-3.3.2-py3-none-any.whl", hash = "sha256:3e4d1f6587322d2788836a99c69062fbb091331ec940e02d12d179c1d53e25fc"}, +] + [[package]] name = "contourpy" version = "1.2.1" @@ -154,6 +264,17 @@ ufo = ["fs (>=2.2.0,<3)"] unicode = ["unicodedata2 (>=15.1.0)"] woff = ["brotli (>=1.0.1)", "brotlicffi (>=0.8.0)", "zopfli (>=0.1.4)"] +[[package]] +name = "idna" +version = "3.7" +description = "Internationalized Domain Names in Applications (IDNA)" +optional = false +python-versions = ">=3.5" +files = [ + {file = "idna-3.7-py3-none-any.whl", hash = "sha256:82fee1fc78add43492d3a1898bfa6d8a904cc97d8427f683ed8e798d07761aa0"}, + {file = "idna-3.7.tar.gz", hash = "sha256:028ff3aadf0609c1fd278d8ea3089299412a7a8b9bd005dd08b9f8285bcb5cfc"}, +] + [[package]] name = "jinja2" version = "3.1.4" @@ -717,6 +838,27 @@ files = [ {file = "pytz-2024.1.tar.gz", hash = "sha256:2a29735ea9c18baf14b448846bde5a48030ed267578472d8955cd0e7443a9812"}, ] +[[package]] +name = "requests" +version = "2.32.3" +description = "Python HTTP for Humans." +optional = false +python-versions = ">=3.8" +files = [ + {file = "requests-2.32.3-py3-none-any.whl", hash = "sha256:70761cfe03c773ceb22aa2f671b4757976145175cdfca038c02654d061d6dcc6"}, + {file = "requests-2.32.3.tar.gz", hash = "sha256:55365417734eb18255590a9ff9eb97e9e1da868d4ccd6402399eaf68af20a760"}, +] + +[package.dependencies] +certifi = ">=2017.4.17" +charset-normalizer = ">=2,<4" +idna = ">=2.5,<4" +urllib3 = ">=1.21.1,<3" + +[package.extras] +socks = ["PySocks (>=1.5.6,!=1.5.7)"] +use-chardet-on-py3 = ["chardet (>=3.0.2,<6)"] + [[package]] name = "scipy" version = "1.14.0" @@ -817,7 +959,24 @@ files = [ {file = "tzdata-2024.1.tar.gz", hash = "sha256:2674120f8d891909751c38abcdfd386ac0a5a1127954fbc332af6b5ceae07efd"}, ] +[[package]] +name = "urllib3" +version = "2.2.2" +description = "HTTP library with thread-safe connection pooling, file post, and more." +optional = false +python-versions = ">=3.8" +files = [ + {file = "urllib3-2.2.2-py3-none-any.whl", hash = "sha256:a448b2f64d686155468037e1ace9f2d2199776e17f0a46610480d311f73e3472"}, + {file = "urllib3-2.2.2.tar.gz", hash = "sha256:dd505485549a7a552833da5e6063639d0d177c04f23bc3864e41e5dc5f612168"}, +] + +[package.extras] +brotli = ["brotli (>=1.0.9)", "brotlicffi (>=0.8.0)"] +h2 = ["h2 (>=4,<5)"] +socks = ["pysocks (>=1.5.6,!=1.5.7,<2.0)"] +zstd = ["zstandard (>=0.18.0)"] + [metadata] lock-version = "2.0" python-versions = "^3.11" -content-hash = "8c967b87a1a98f8cc988395aca349d801f313d7b9b764477478af221c3f9c09e" +content-hash = "26656ae90d0f011bbf3c85d87845477d05823028811d486b8b37756c40db4885" diff --git a/pyproject.toml b/pyproject.toml index fc242b3..07809df 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,8 +1,8 @@ [tool.poetry] name = "cmp" -version = "0.1.1" -description = "" -authors = ["RobertoChiosa "] +version = "1.0.1" +description = "Contextual matrix profile for anomaly detection in building electrical loads" +authors = ["RobertoChiosa "] readme = "README.md" packages = [ { include = "src/cmp" }, @@ -21,6 +21,7 @@ kneed = "^0.8.5" jinja2 = "^3.1.4" argparse = "^1.4.0" logger = "^1.4" +requests = "^2.32.3" [build-system] diff --git a/src/cmp/anomaly_detection_functions.py b/src/cmp/anomaly_detection_functions.py index 995e287..549f3bf 100644 --- a/src/cmp/anomaly_detection_functions.py +++ b/src/cmp/anomaly_detection_functions.py @@ -1,6 +1,6 @@ # Copyright © Roberto Chiosa 2024. # Email: roberto.chiosa@polito.it -# Last edited: 16/7/2024 +# Last edited: 13/8/2024 import matplotlib.pyplot as plt import numpy as np @@ -195,10 +195,10 @@ def gesd_esd_test(input_series, max_outliers, alpha=0.05): # Calculates the statistical test Ri = max_i*(x_i-x_bar)/sts_dv(x_i) max_ind = np.argmax(abs(input_series - np.mean(input_series))) - R_i = max(abs(input_series - np.mean(input_series))) / np.std(input_series) + r_i = max(abs(input_series - np.mean(input_series))) / np.std(input_series) # print('Test {}'.format(iteration)) - # print("Test Statistics Value(R{}) : {}".format(iteration, R_i)) + # print("Test Statistics Value(R{}) : {}".format(iteration, r_i)) # compute the critical values # 1- alpha/(2*(A+1)) A=n-i B=tp,n-i-1 i=1....r @@ -210,19 +210,19 @@ def gesd_esd_test(input_series, max_outliers, alpha=0.05): # print("Critical Value(λ{}): {}".format(iteration, critical_value)) # # check values from function - # if R_i > lambda_i: # R > C: + # if r_i > lambda_i: # R > C: # print('{} is an outlier. R{} > λ{}: {:.4f} > {:.4f} \n'.format(input_series[max_ind], i, - # i, R_i, lambda_i)) + # i, r_i, lambda_i)) # else: # print( # '{} is not an outlier. R{}> λ{}: {:.4f} > {:.4f} \n'.format(input_series[max_ind], i, - # i, R_i, lambda_i)) + # i, r_i, lambda_i)) input_series = np.delete(input_series, max_ind) critical_values.append(lambda_i) - stats_1.append(R_i) + stats_1.append(r_i) # The number of outliers is determined by finding the largest i such that Ri > lambda_i. - if R_i > lambda_i: + if r_i > lambda_i: n_outliers = i # print('H0: there are no outliers in the data') diff --git a/src/cmp/data/group_cluster.csv b/src/cmp/data/group_cluster.csv new file mode 100644 index 0000000..00b2c8e --- /dev/null +++ b/src/cmp/data/group_cluster.csv @@ -0,0 +1,366 @@ +"timestamp","Cluster_1","Cluster_2","Cluster_3","Cluster_4","Cluster_5" +"2019-01-01",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-02",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-03",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-04",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-01-05",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-01-06",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-07",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-09",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-10",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-12",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-01-13",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-14",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-16",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-17",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-19",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-01-20",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-21",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-22",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-23",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-24",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-25",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-26",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-01-27",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-01-28",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-29",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-30",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-01-31",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-01",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-02",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-02-03",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-02-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-07",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-09",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-02-10",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-02-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-14",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-16",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-02-17",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-02-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-19",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-21",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-22",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-23",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-02-24",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-02-25",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-26",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-27",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-02-28",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-01",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-02",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-03-03",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-03-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-07",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-09",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-03-10",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-03-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-14",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-16",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-03-17",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-03-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-19",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-21",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-22",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-23",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-03-24",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-03-25",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-26",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-27",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-28",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-29",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-03-30",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-03-31",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-01",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-02",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-03",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-06",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-04-07",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-09",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-10",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-13",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-04-14",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-16",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-04-17",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-18",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-19",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-20",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-21",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-22",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-23",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-24",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-25",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-26",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-27",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-28",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-04-29",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-04-30",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-01",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-02",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-03",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-04",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-05",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-06",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-07",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-09",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-10",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-11",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-05-12",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-14",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-15",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-16",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-17",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-18",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-19",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-21",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-22",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-23",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-24",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-25",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-05-26",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-05-27",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-28",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-29",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-05-30",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-05-31",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-06-01",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-06-02",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-06-03",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-05",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-06-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-07",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-08",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-06-09",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-06-10",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-14",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-15",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-06-16",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-06-17",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-19",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-06-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-21",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-06-22",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-06-23",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-06-24",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-06-25",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-06-26",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-06-27",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-06-28",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-06-29",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-06-30",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-07-01",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-02",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-03",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-04",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-05",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-06",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-07-07",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-07-08",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-09",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-10",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-11",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-12",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-13",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-07-14",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-07-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-07-16",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-07-17",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-18",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-19",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-20",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-07-21",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-07-22",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-23",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-24",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-25",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-26",FALSE,FALSE,FALSE,FALSE,TRUE +"2019-07-27",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-07-28",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-07-29",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-07-30",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-07-31",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-08-01",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-08-02",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-03",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-08-04",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-08-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-08-07",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-08",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-09",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-10",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-08-11",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-12",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-13",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-14",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-15",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-16",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-17",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-18",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-19",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-20",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-21",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-22",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-23",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-24",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-08-25",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-08-26",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-27",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-28",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-08-29",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-08-30",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-08-31",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-09-01",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-09-02",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-03",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-07",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-09-08",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-09-09",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-10",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-14",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-09-15",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-09-16",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-17",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-19",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-21",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-09-22",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-09-23",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-24",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-25",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-26",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-27",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-09-28",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-09-29",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-09-30",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-01",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-02",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-03",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-05",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-10-06",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-10-07",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-09",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-10",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-12",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-10-13",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-10-14",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-16",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-17",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-19",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-10-20",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-10-21",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-22",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-23",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-24",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-25",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-26",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-10-27",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-10-28",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-29",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-30",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-10-31",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-01",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-11-02",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-11-03",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-11-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-07",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-08",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-09",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-11-10",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-11-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-14",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-15",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-16",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-11-17",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-11-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-19",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-21",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-22",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-23",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-11-24",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-11-25",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-26",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-27",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-28",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-29",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-11-30",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-12-01",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-02",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-03",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-04",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-05",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-06",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-07",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-12-08",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-09",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-10",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-11",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-12",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-13",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-14",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-12-15",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-16",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-17",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-18",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-19",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-20",FALSE,FALSE,FALSE,TRUE,FALSE +"2019-12-21",FALSE,TRUE,FALSE,FALSE,FALSE +"2019-12-22",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-23",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-12-24",FALSE,FALSE,TRUE,FALSE,FALSE +"2019-12-25",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-26",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-27",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-28",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-29",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-30",TRUE,FALSE,FALSE,FALSE,FALSE +"2019-12-31",TRUE,FALSE,FALSE,FALSE,FALSE diff --git a/src/cmp/data/time_window_corrected.csv b/src/cmp/data/time_window_corrected.csv new file mode 100644 index 0000000..0f83a10 --- /dev/null +++ b/src/cmp/data/time_window_corrected.csv @@ -0,0 +1,6 @@ +"id","description","observations","from","to","duration","node" +1,[00:00 - 06:30),26,"00:00",06:30,"22500s (~6.25 hours)","Node 2" +2,[06:30 - 09:00),10,06:30,09:00,"9000s (~2.5 hours)","Node 6" +3,[09:00 - 15:45),27,09:00,15:45,"24300s (~6.75 hours)","Node 9" +4,[15:45 - 19:15),14,15:45,19:15,"12600s (~3.5 hours)","Node 8" +5,[19:15 - 24:00),19,19:15,"24:00","18000s (~5 hours)","Node 4" diff --git a/src/cmp/main.py b/src/cmp/main.py index c5aca85..334cc8b 100644 --- a/src/cmp/main.py +++ b/src/cmp/main.py @@ -1,24 +1,17 @@ # Copyright © Roberto Chiosa 2024. # Email: roberto.chiosa@polito.it -# Last edited: 13/8/2024 +# Last edited: 17/9/2024 + import argparse -# import from default libraries and packages import datetime # data from statistics import mean -# import matplotlib.pyplot as plt # plots import plotly.express as px -# import scipy.stats as stats from scipy.stats import zscore - from src.cmp.anomaly_detection_functions import anomaly_detection, extract_vector_ad_temperature, \ extract_vector_ad_energy, extract_vector_ad_cmp -# from src.distancematrix.generator import Euclidean -# import from custom modules useful functions from src.cmp.utils import * -# import from the local module distancematrix from src.distancematrix.calculator import AnytimeCalculator -# from src.distancematrix.consumer import ContextualMatrixProfile from src.distancematrix.consumer.contextmanager import GeneralStaticManager from src.distancematrix.consumer.contextual_matrix_profile import ContextualMatrixProfile from src.distancematrix.generator.euclidean import Euclidean @@ -88,11 +81,12 @@ # The number of time window has been selected from CART on total electrical power, # results are contained in 'time_window.csv' file + # todo perform cart and create dataframe accordingly df_time_window = pd.read_csv(os.path.join(path_to_data, "time_window_corrected.csv")) # The context is defined as 1 hour before time window, to be consistent with other analysis, # results are loaded from 'm_context.csv' file - m_context = pd.read_csv(os.path.join(path_to_data, "m_context.csv"))["m_context"][0] + m_context = 1 # Define output files as dataframe # - df_anomaly_results -> in this file the anomaly results will be saved @@ -119,11 +113,13 @@ context_start = context_end - m_context # [hours] # print string to explain the created context in an intelligible way - context_string = f'Subsequences of {dec_to_hour(m / obs_per_hour)} h (m = {m}) that start in [{dec_to_hour(context_start)},{dec_to_hour(context_end)})' + context_string = (f'Subsequences of {dec_to_hour(m / obs_per_hour)} h (m = {m}) that ' + f'start in [{dec_to_hour(context_start)},{dec_to_hour(context_end)})') # contracted context string for names - context_string_small = f'ctx_from{dec_to_hour(context_start)}_to{dec_to_hour(context_end)}_m{dec_to_hour(m / obs_per_hour)}'.replace( - ":", "_") + context_string_small = (f'ctx_from{dec_to_hour(context_start)}_' + f'to{dec_to_hour(context_end)}_m{dec_to_hour(m / obs_per_hour)}' + ).replace(":", "_") # update context dataframe df_contexts.loc[id_tw] = [ @@ -208,6 +204,7 @@ }) ######################################################################################## + # todo perform cluster analysis # Load Cluster results as boolean dataframe: each column represents a group group_df = pd.read_csv(os.path.join(path_to_data, "group_cluster.csv"), index_col='timestamp', parse_dates=True) # initialize dataframe of results for context to be appended to the overall result @@ -322,7 +319,12 @@ report_content['contexts'][id_tw]["clusters"].append({ "title": f"Cluster {id_cluster + 1}", - "content": f"The current cluster contains {len(group_dates)} days and {num_anomalies_to_show} anomalies identified in the context defines as {context_string.lower()}. The plot referring to the cluster and relative anomaly (if any) are reported in the line-plot below. The red line refers to the anomalous day, while the light orange box refers to the time window {id_tw + 1} and the dark orange the context under analysis.", + "content": f"The current cluster contains {len(group_dates)} days and " + f"{num_anomalies_to_show} anomalies " + f"identified in the context defines as {context_string.lower()}. The plot referring to the " + f"cluster and relative anomaly (if any) are reported in the line-plot below. The red line " + f"refers to the anomalous day, while the light orange box refers to the time " + f"window {id_tw + 1} and the dark orange the context under analysis.", "plot": fig.to_html(full_html=False), "table": anomalies_table.to_html(index=False, classes='table table-striped table-hover', diff --git a/src/cmp/templates/cmp.html b/src/cmp/templates/cmp.html new file mode 100644 index 0000000..bae7113 --- /dev/null +++ b/src/cmp/templates/cmp.html @@ -0,0 +1,87 @@ + + + + + + {{ title }} + + + + + + +
+ +
+ +
+

{{ title }}

+

{{ subtitle }}

+
+ + +
+

{{ summary.title }}

+

{{ summary.content }}

+ {{ summary.plot }} +
+ + + {% for context in contexts %} +
+
+
+
+

{{ context.title }}

+

{{ context.subtitle }}

+

{{ context.content }}

+
+
+ {{ context.plot }} +
+
+ {% for cluster in context.clusters %} + + {% if cluster.plot_anomalies %} +
+
+

{{ cluster.title }}

+

{{ cluster.content }}

+ {{cluster.table}} +
+
+
+
+ {{ cluster.plot_anomalies }} +
+
+ {{ cluster.plot }} +
+
+ + + {% else %} +
+
+

{{ cluster.title }}

+

{{ cluster.content }}

+
+
+ {{ cluster.plot }} +
+
+ {% endif %} + + {% endfor %} +
+ {% endfor %} + + + +
+ + +
+ diff --git a/src/cmp/utils.py b/src/cmp/utils.py index 54f336c..67f9539 100644 --- a/src/cmp/utils.py +++ b/src/cmp/utils.py @@ -10,6 +10,7 @@ import matplotlib.ticker as mticker import numpy as np import pandas as pd +import requests from jinja2 import Environment, FileSystemLoader # Path to folders @@ -65,14 +66,20 @@ def download_data(filepath: str) -> pd.DataFrame: Download data from a user specified path The input dataset via an HTTP URL. The tool should then download the dataset from that URL; - since it's a presigned URL, the tool would not need to deal with authentication—it can just download + since it's a pre-signed URL, the tool would not need to deal with authentication—it can just download the dataset directly. :param filepath: :return: data """ - logger.info(f"⬇️ Downloading file from <{filepath}>") - data = pd.read_csv(filepath) + # if filepath is an url request otherwise read from file + if filepath.startswith('http'): + logger.info(f"⬇️ Downloading file from online url <{filepath}>") + res = requests.get(filepath) + data = pd.read_csv(res.text) + else: + logger.info(f"⬇️ Reading local file from <{filepath}> path") + data = pd.read_csv(filepath) return data @@ -109,11 +116,10 @@ def process_data(data_raw: pd.DataFrame, variable: str) -> tuple: raise -def ensure_dir(dir_path): +def ensure_dir(dir_path: str) -> None: """Ensures that the directory exists - :param file_path: path to the file - :type file_path: str + :param dir_path: path to the file :example: >>> ensure_dir('data/processed') @@ -122,7 +128,7 @@ def ensure_dir(dir_path): os.makedirs(dir_path) -def hour_to_dec(hour_str): +def hour_to_dec(hour_str: str) -> float: """ Transforms float hours from HH:MM string format to float with decimal places :param hour_str: hour in format HH:MM @@ -141,7 +147,7 @@ def hour_to_dec(hour_str): return hour_dec -def dec_to_hour(hour_dec): +def dec_to_hour(hour_dec: float) -> str: """ Transforms float hours with decimal places into HH:MM string format :param hour_dec: hour in numerical format @@ -224,7 +230,7 @@ def nan_diag(matrix): return matrix_nan -def CMP_plot(contextual_mp, +def cmp_plot(contextual_mp, palette="viridis", title=None, xlabel=None,