Skip to content

Commit

Permalink
feat: separate cells (#14)
Browse files Browse the repository at this point in the history
  • Loading branch information
@ReenigneArcher
ReenigneArcher authored Aug 21, 2024
1 parent 34ae300 commit 0e7ec32
Showing 1 changed file with 99 additions and 44 deletions.
143 changes: 99 additions & 44 deletions notebook/dashboard.ipynb
View file
Original file line number Diff line number Diff line change
Expand Up @@ -71,11 +71,11 @@
{
"cell_type": "code",
"execution_count": null,
"id": "initial_id",
"id": "957d644a7520fbd",
"metadata": {},
"outputs": [],
"source": [
"# Initialize the environment\n",
"# Imports\n",
"\n",
"# standard imports\n",
"import os\n",
Expand All @@ -88,7 +88,17 @@
"import plotly.express as px\n",
"import plotly.graph_objects as go\n",
"import plotly.io as pio\n",
"import requests\n",
"import requests"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "initial_id",
"metadata": {},
"outputs": [],
"source": [
"# Setup the environment\n",
"\n",
"# Load environment variables from .env file\n",
"load_dotenv()\n",
Expand All @@ -99,6 +109,7 @@
"\n",
"# set the default plotly template\n",
"pio.templates.default = \"plotly_dark\"\n",
"pio.renderers.default = 'notebook'\n",
"\n",
"# Fetch repository data\n",
"org_name = \"LizardByte\"\n",
Expand All @@ -115,9 +126,17 @@
"readthedocs_response = requests.get(readthedocs_data_url)\n",
"if not readthedocs_response.ok:\n",
" raise LookupError(\"Failed to fetch data from uno\")\n",
"readthedocs_data = readthedocs_response.json()\n",
"\n",
"# Process data\n",
"readthedocs_data = readthedocs_response.json()"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "3d804270c89d8280",
"metadata": {},
"outputs": [],
"source": [
"# Get Repo Data\n",
"repo_data = []\n",
"for repo in repos:\n",
" # get license\n",
Expand Down Expand Up @@ -171,7 +190,17 @@
" \"has_readthedocs\": readthedocs_project is not None,\n",
" \"has_readme\": readme_file is not None,\n",
" \"_repo\": repo,\n",
" })\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "55ae039e9f91e18",
"metadata": {},
"outputs": [],
"source": [
"# Initial data frames\n",
"\n",
"df = pd.DataFrame(repo_data)\n",
"df_repos = df[\n",
Expand All @@ -182,12 +211,20 @@
" (~df['archived']) &\n",
" (~df['fork']) &\n",
" (~df['topics'].apply(lambda topics: 'package-manager' in topics))\n",
"]\n",
"\n",
"]"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "466d0d2fec2e1828",
"metadata": {},
"outputs": [],
"source": [
"# Initial Results\n",
"print(f'Total Repositories: {len(repo_data)}')\n",
"print(f'Archived Repositories: {df[\"archived\"].sum()}')\n",
"print(f'Forked Repositories: {df[\"fork\"].sum()}')\n",
"\n",
"print(f'Total Open Issues: {df[\"issues\"].apply(len).sum()}')\n",
"print(f'Total Open PRs: {df[\"prs\"].apply(len).sum()}')\n",
"print(f'Open issues in active repositories: {df_repos[\"issues\"].apply(len).sum()}')\n",
Expand Down Expand Up @@ -236,30 +273,33 @@
{
"cell_type": "code",
"execution_count": null,
"id": "a08398efe666a399",
"id": "6ce69f164706dacf",
"metadata": {},
"outputs": [],
"source": [
"# Star History\n",
"# Star History Data\n",
"stargazer_data = []\n",
"for repo in df_repos.to_dict('records'):\n",
" stargazers = repo['_repo'].get_stargazers_with_dates()\n",
" for stargazer in stargazers:\n",
" stargazer_data.append({\n",
" \"repo\": repo['repo'],\n",
" \"date\": stargazer.starred_at,\n",
" })\n",
"\n",
"# Convert to DataFrame\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "a08398efe666a399",
"metadata": {},
"outputs": [],
"source": [
"# Star History Visuals\n",
"df_stargazers = pd.DataFrame(stargazer_data)\n",
"\n",
"# Sort by date\n",
"df_stargazers = df_stargazers.sort_values(by=\"date\")\n",
"\n",
"# Calculate cumulative stars\n",
"df_stargazers[\"cumulative_stars\"] = df_stargazers.groupby(\"repo\").cumcount() + 1\n",
"\n",
"# Visualize using Plotly\n",
"fig = px.line(\n",
" df_stargazers,\n",
" x=\"date\",\n",
Expand All @@ -268,7 +308,6 @@
" title=\"Star History\",\n",
" labels={\"date\": \"Date\", \"cumulative_stars\": \"Cumulative Stars\"},\n",
")\n",
"\n",
"fig.show()"
]
},
Expand Down Expand Up @@ -360,11 +399,11 @@
{
"cell_type": "code",
"execution_count": null,
"id": "4f473fe7a839b01c",
"id": "3bde60fbd0b7e540",
"metadata": {},
"outputs": [],
"source": [
"# Open PRs\n",
"# PR Data\n",
"pr_data = []\n",
"for repo in df_repos.to_dict('records'):\n",
" draft_prs = 0\n",
Expand All @@ -385,15 +424,21 @@
" \"Draft\": draft_prs,\n",
" \"Ready for review\": non_draft_prs,\n",
" \"Dependency\": dependabot_prs,\n",
" })\n",
"\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "4f473fe7a839b01c",
"metadata": {},
"outputs": [],
"source": [
"# Open PRs\n",
"df_prs = pd.DataFrame(pr_data)\n",
"df_prs['total_prs'] = df_prs[['Draft', 'Ready for review', 'Dependency']].sum(axis=1)\n",
"\n",
"# Sort by total PRs in descending order\n",
"df_prs = df_prs.sort_values(by='total_prs', ascending=False)\n",
"\n",
"# Visualize data using a stacked bar chart\n",
"fig = px.bar(\n",
" df_prs,\n",
" x='repo',\n",
Expand Down Expand Up @@ -427,7 +472,6 @@
"# License distribution\n",
"license_counts = df_repos.groupby(['license', 'repo']).size().reset_index(name='count')\n",
"\n",
"# Create a nested treemap for license distribution with repo names in hover data\n",
"fig_treemap = px.treemap(\n",
" license_counts,\n",
" path=['license', 'repo'],\n",
Expand Down Expand Up @@ -484,27 +528,35 @@
{
"cell_type": "code",
"execution_count": null,
"id": "20e09d93eda0478a",
"id": "2cf8ff484b1639d",
"metadata": {},
"outputs": [],
"source": [
"# Programming Languages by Bytes of Code\n",
"# Programming language data\n",
"language_data = []\n",
"for repo in df_repos.to_dict('records'):\n",
" for language, bytes_of_code in repo['languages'].items():\n",
" language_data.append({\n",
" \"repo\": repo['repo'],\n",
" \"language\": language,\n",
" \"bytes_of_code\": bytes_of_code,\n",
" })\n",
"\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "20e09d93eda0478a",
"metadata": {},
"outputs": [],
"source": [
"# Programming Languages\n",
"df_languages = pd.DataFrame(language_data)\n",
"\n",
"# Aggregate data by language and repo\n",
"language_counts_bytes = df_languages.groupby(['language', 'repo']).agg({\n",
" 'bytes_of_code': 'sum'\n",
"}).reset_index()\n",
"\n",
"language_counts_repos = df_languages.groupby(['language', 'repo']).size().reset_index(name='repo_count')\n",
"\n",
"def create_language_figures(counts: pd.DataFrame, path_key: str, value_key: str):\n",
Expand Down Expand Up @@ -560,7 +612,6 @@
" }\n",
" ]\n",
" )\n",
"\n",
" fig.show()"
]
},
Expand All @@ -575,24 +626,29 @@
{
"cell_type": "code",
"execution_count": null,
"id": "ec43a8fd7f9d49bb",
"id": "e7ba218e5863deb7",
"metadata": {},
"outputs": [],
"source": [
"# Docs\n",
"\n",
"# Initialize an empty list\n",
"# Docs data\n",
"docs_data = []\n",
"for repo in df_repos.to_dict('records'):\n",
" docs_data.append({\n",
" \"repo\": repo['repo'],\n",
" \"has_readme\": repo['has_readme'],\n",
" \"has_readthedocs\": repo['has_readthedocs'],\n",
" })\n",
"\n",
" })"
]
},
{
"cell_type": "code",
"execution_count": null,
"id": "ec43a8fd7f9d49bb",
"metadata": {},
"outputs": [],
"source": [
"# Docs\n",
"df_docs = pd.DataFrame(docs_data)\n",
"\n",
"# Aggregate data by has_readme/has_readthedocs and repo\n",
"readme_counts = df_docs.groupby(['has_readme', 'repo']).size().reset_index(name='repo_count')\n",
"readthedocs_counts = df_docs.groupby(['has_readthedocs', 'repo']).size().reset_index(name='repo_count')\n",
"\n",
Expand Down Expand Up @@ -645,7 +701,6 @@
" }\n",
" ]\n",
" )\n",
"\n",
" fig.show()"
]
}
Expand Down

0 comments on commit 0e7ec32

Please sign in to comment.