fix(ci): green initial commit — uv.lock + ruff-clean notebooks

notebooks/01_load_data.ipynb

@@ -2,6 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {},
    "source": [
     "# 01 — Load data\n",
@@ -14,23 +15,26 @@
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "acae54e37e7d407bbb7b55eff062a284",
    "metadata": {},
    "outputs": [],
    "source": [
     "import sys\n",
     "from pathlib import Path\n",
+    "\n",
     "sys.path.insert(0, str(Path.cwd().parent))\n",
     "\n",
     "from src.utils import load_csv\n",
     "\n",
-    "df = load_csv('../data/raw/population_africa_sample.csv')\n",
+    "df = load_csv(\"../data/raw/population_africa_sample.csv\")\n",
     "print(df.shape)\n",
     "df.head()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "9a63283cbaf04dbcab1f6479b197f3a8",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -40,6 +44,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "8dd0d8092fe74a7c96281538738b07e2",
    "metadata": {},
    "outputs": [],
    "source": [
@@ -48,8 +53,15 @@
   }
  ],
  "metadata": {
-  "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" },
-  "language_info": { "name": "python", "version": "3.12" }
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 5

notebooks/02_basic_analysis.ipynb

@@ -2,6 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {},
    "source": [
     "# 02 — Basic analysis\n",
@@ -14,64 +15,77 @@
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "acae54e37e7d407bbb7b55eff062a284",
    "metadata": {},
    "outputs": [],
    "source": [
     "import sys\n",
     "from pathlib import Path\n",
+    "\n",
     "sys.path.insert(0, str(Path.cwd().parent))\n",
     "\n",
     "import matplotlib.pyplot as plt\n",
     "import seaborn as sns\n",
+    "\n",
     "from src.utils import load_csv, summary_stats, top_n\n",
     "\n",
-    "df = load_csv('../data/raw/population_africa_sample.csv')\n",
+    "df = load_csv(\"../data/raw/population_africa_sample.csv\")\n",
     "df.head()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "9a63283cbaf04dbcab1f6479b197f3a8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "by_region = summary_stats(df, 'region', 'population_millions')\n",
+    "by_region = summary_stats(df, \"region\", \"population_millions\")\n",
     "by_region"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "8dd0d8092fe74a7c96281538738b07e2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "top = top_n(df, 'population_millions', n=5)\n",
+    "top = top_n(df, \"population_millions\", n=5)\n",
     "\n",
-    "sns.set_theme(style='darkgrid')\n",
+    "sns.set_theme(style=\"darkgrid\")\n",
     "fig, ax = plt.subplots(figsize=(8, 4))\n",
-    "sns.barplot(data=top, x='country', y='population_millions', ax=ax)\n",
-    "ax.set_title('Top 5 by population — sample data')\n",
+    "sns.barplot(data=top, x=\"country\", y=\"population_millions\", ax=ax)\n",
+    "ax.set_title(\"Top 5 by population — sample data\")\n",
     "plt.tight_layout()\n",
     "plt.show()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "72eea5119410473aa328ad9291626812",
    "metadata": {},
    "outputs": [],
    "source": [
     "fig, ax = plt.subplots(figsize=(6, 4))\n",
-    "sns.scatterplot(data=df, x='population_millions', y='gdp_per_capita_usd', hue='region', ax=ax)\n",
-    "ax.set_title('Population vs GDP per capita')\n",
+    "sns.scatterplot(data=df, x=\"population_millions\", y=\"gdp_per_capita_usd\", hue=\"region\", ax=ax)\n",
+    "ax.set_title(\"Population vs GDP per capita\")\n",
     "plt.tight_layout()\n",
     "plt.show()"
    ]
   }
  ],
  "metadata": {
-  "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" },
-  "language_info": { "name": "python", "version": "3.12" }
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 5

notebooks/03_duckdb_queries.ipynb

@@ -2,6 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {},
    "source": [
     "# 03 — DuckDB queries\n",
@@ -14,52 +15,63 @@
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "acae54e37e7d407bbb7b55eff062a284",
    "metadata": {},
    "outputs": [],
    "source": [
     "import duckdb\n",
     "\n",
     "con = duckdb.connect()\n",
-    "con.execute(\"CREATE OR REPLACE VIEW pop AS SELECT * FROM read_csv_auto('../data/raw/population_africa_sample.csv')\")\n",
-    "con.sql('SELECT * FROM pop LIMIT 5').df()"
+    "csv_path = \"../data/raw/population_africa_sample.csv\"\n",
+    "con.execute(f\"CREATE OR REPLACE VIEW pop AS SELECT * FROM read_csv_auto('{csv_path}')\")\n",
+    "con.sql(\"SELECT * FROM pop LIMIT 5\").df()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "9a63283cbaf04dbcab1f6479b197f3a8",
    "metadata": {},
    "outputs": [],
    "source": [
-    "con.sql('''\n",
+    "con.sql(\"\"\"\n",
     "  SELECT region,\n",
     "         COUNT(*) AS n_countries,\n",
     "         SUM(population_millions) AS total_pop_m,\n",
     "         ROUND(AVG(gdp_per_capita_usd), 0) AS avg_gdp_per_capita\n",
     "  FROM pop\n",
     "  GROUP BY region\n",
     "  ORDER BY total_pop_m DESC\n",
-    "''').df()"
+    "\"\"\").df()"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "8dd0d8092fe74a7c96281538738b07e2",
    "metadata": {},
    "outputs": [],
    "source": [
-    "con.sql('''\n",
+    "con.sql(\"\"\"\n",
     "  SELECT country, population_millions, gdp_per_capita_usd\n",
     "  FROM pop\n",
     "  WHERE gdp_per_capita_usd > 2000\n",
     "  ORDER BY gdp_per_capita_usd DESC\n",
-    "''').df()"
+    "\"\"\").df()"
    ]
   }
  ],
  "metadata": {
-  "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" },
-  "language_info": { "name": "python", "version": "3.12" }
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}

notebooks/04_ml_intro.ipynb

@@ -2,6 +2,7 @@
  "cells": [
   {
    "cell_type": "markdown",
+   "id": "7fb27b941602401d91542211134fc71a",
    "metadata": {},
    "source": [
     "# 04 — ML intro\n",
@@ -14,41 +15,45 @@
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "acae54e37e7d407bbb7b55eff062a284",
    "metadata": {},
    "outputs": [],
    "source": [
     "import sys\n",
     "from pathlib import Path\n",
+    "\n",
     "sys.path.insert(0, str(Path.cwd().parent))\n",
     "\n",
-    "import numpy as np\n",
     "from sklearn.linear_model import LinearRegression\n",
-    "from sklearn.model_selection import train_test_split\n",
     "from sklearn.metrics import mean_absolute_error, r2_score\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "\n",
     "from src.utils import load_csv\n",
     "\n",
-    "df = load_csv('../data/raw/population_africa_sample.csv')\n",
-    "X = df[['population_millions']].to_numpy()\n",
-    "y = df['gdp_per_capita_usd'].to_numpy()\n",
+    "df = load_csv(\"../data/raw/population_africa_sample.csv\")\n",
+    "X = df[[\"population_millions\"]].to_numpy()\n",
+    "y = df[\"gdp_per_capita_usd\"].to_numpy()\n",
     "\n",
     "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.3, random_state=42)"
    ]
   },
   {
    "cell_type": "code",
    "execution_count": null,
+   "id": "9a63283cbaf04dbcab1f6479b197f3a8",
    "metadata": {},
    "outputs": [],
    "source": [
     "model = LinearRegression().fit(X_train, y_train)\n",
     "y_pred = model.predict(X_test)\n",
-    "print('MAE:', mean_absolute_error(y_test, y_pred))\n",
-    "print('R2:', r2_score(y_test, y_pred))\n",
-    "print('coef:', model.coef_, 'intercept:', model.intercept_)"
+    "print(\"MAE:\", mean_absolute_error(y_test, y_pred))\n",
+    "print(\"R2:\", r2_score(y_test, y_pred))\n",
+    "print(\"coef:\", model.coef_, \"intercept:\", model.intercept_)"
    ]
   },
   {
    "cell_type": "markdown",
+   "id": "8dd0d8092fe74a7c96281538738b07e2",
    "metadata": {},
    "source": [
     "> With a 17-row toy dataset this model is essentially meaningless — the point is to show the sklearn API, not to draw conclusions.\n",
@@ -58,8 +63,15 @@
   }
  ],
  "metadata": {
-  "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" },
-  "language_info": { "name": "python", "version": "3.12" }
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.12"
+  }
  },
  "nbformat": 4,
  "nbformat_minor": 5

src/utils.py

@@ -2,6 +2,7 @@
 
 Keep functions here pure and tested — notebooks should only orchestrate them.
 """
+
 from __future__ import annotations
 
 from pathlib import Path