jrpybestpracccc 0.1.1__tar.gz

jrpybestpracccc-0.1.1/PKG-INFO

@@ -0,0 +1,14 @@
+Metadata-Version: 2.1
+Name: jrpybestpracccc
+Version: 0.1.1
+Summary: Jumping Rivers: Python Best Practices
+Author: Jumping Rivers
+Author-email: info@jumpingrivers.com
+Requires-Python: >=3.10
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Requires-Dist: jrpybestprac (>=0.1.3)
+Requires-Dist: plotly (>=6.0.0)
+Requires-Dist: scikit-learn (>=1.1.1)

jrpybestpracccc-0.1.1/jrpybestpracccc/__init__.py

@@ -0,0 +1,3 @@
+from .__version__ import __version__  # noqa: F401
+
+from . import vignettes  # noqa: F401

jrpybestpracccc-0.1.1/jrpybestpracccc/__version__.py

@@ -0,0 +1 @@
+__version__ = "0.1.1"

jrpybestpracccc-0.1.1/jrpybestpracccc/extra_scripts/example_projects/bad_project/.gitignore

@@ -0,0 +1,3 @@
+*.csv
+*__pycache__/
+

jrpybestpracccc-0.1.1/jrpybestpracccc/extra_scripts/example_projects/bad_project/experiment.ipynb

@@ -0,0 +1,193 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "051b5e69",
+   "metadata": {},
+   "source": [
+    "# Experimental Notebook"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ce57b322",
+   "metadata": {},
+   "source": [
+    "## Data loading"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "b155d9e6",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import pandas as pd\n",
+    "\n",
+    "\n",
+    "# Load raw data\n",
+    "archetype_df = pd.read_csv(\n",
+    "    \"data/Baseline archetype properties.csv\"\n",
+    ")\n",
+    "\n",
+    "# Skip the first 4 rows as they contain metadata or headers not relevant to the DataFrame\n",
+    "fixed_capex_df = pd.read_csv(\n",
+    "    \"data/Input Baseline capex fixed.csv\",\n",
+    "    skiprows=4,\n",
+    ")\n",
+    "# Skip the first 4 rows as they contain metadata or headers not relevant to the DataFrame\n",
+    "capex_by_power_df = pd.read_csv(\n",
+    "    \"data/Input Baseline capex by power.csv\",\n",
+    "    skiprows=4,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ef90ee7d",
+   "metadata": {},
+   "source": [
+    "## Data preprocessing"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5d787f54",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Preprocess data\n",
+    "fixed_capex_df = fixed_capex_df.merge(\n",
+    "    archetype_df,\n",
+    "    left_on=\"Heating system\",\n",
+    "    right_on=\"Heating system\",\n",
+    "    how=\"inner\",\n",
+    ")\n",
+    "\n",
+    "capex_by_power_df = capex_by_power_df.merge(\n",
+    "    archetype_df,\n",
+    "    left_on=\"Heating system\",\n",
+    "    right_on=\"Heating system\",\n",
+    "    how=\"inner\",\n",
+    ")\n",
+    "\n",
+    "year_cols = [col for col in capex_by_power_df.columns if col.startswith(\"20\")]\n",
+    "\n",
+    "capex_by_power_df[year_cols] = capex_by_power_df[year_cols].multiply(\n",
+    "    capex_by_power_df[\"Heating system size\"], axis=0\n",
+    ")\n",
+    "\n",
+    "all_capex_df =pd.concat([capex_by_power_df, fixed_capex_df])\n",
+    "\n",
+    "year_cols = [col for col in all_capex_df.columns if col.startswith(\"20\")]\n",
+    "agg_dict = {col: 'first' for col in all_capex_df.columns if col not in year_cols}\n",
+    "agg_dict.update({col: 'sum' for col in year_cols})\n",
+    "\n",
+    "all_capex_df = all_capex_df.groupby(by=\"Constrained archetype number\", as_index=False).agg(agg_dict)\n",
+    "\n",
+    "columns_to_drop = [\n",
+    "    \"Cost type variant\",\n",
+    "    \"Assumptions\",\n",
+    "    \"Heating system\",\n",
+    "]\n",
+    "\n",
+    "all_capex_df = all_capex_df.drop(columns=columns_to_drop)\n",
+    "\n",
+    "all_capex_df[\"Variable unit\"] = \"£\"\n",
+    "\n",
+    "all_capex_df[\"Data name\"] = \"Baseline capex per home by renewal year\"\n",
+    "\n",
+    "all_capex_df.to_csv(\"data/Baseline heating system capex.csv\", index=False)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "4e058f29",
+   "metadata": {},
+   "source": [
+    "## Data modelling"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "0cd24f13",
+   "metadata": {},
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "638.7722752913661"
+      ]
+     },
+     "execution_count": 4,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "from sklearn.linear_model import LinearRegression\n",
+    "from sklearn.metrics import mean_absolute_error\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.preprocessing import OneHotEncoder\n",
+    "\n",
+    "\n",
+    "# Data extraction\n",
+    "target = \"2020\"\n",
+    "predictors = [\n",
+    "    \"Tenure\",\n",
+    "    \"Region\",\n",
+    "    \"Fuel poverty\",\n",
+    "    \"Property type\",\n",
+    "]\n",
+    "\n",
+    "y = all_capex_df[target]\n",
+    "X = all_capex_df[predictors]\n",
+    "\n",
+    "# Train-test split\n",
+    "X_train, X_test, y_train, y_test = train_test_split(\n",
+    "    X, y, test_size=0.2\n",
+    ")\n",
+    "\n",
+    "# Construct the model pipeline\n",
+    "model = Pipeline(\n",
+    "    [\n",
+    "        (\"transform\", OneHotEncoder(drop=\"first\")),\n",
+    "        (\"model\", LinearRegression()),\n",
+    "    ]\n",
+    ")\n",
+    "\n",
+    "# Fit the model\n",
+    "model.fit(X_train, y_train)\n",
+    "\n",
+    "# Test the model\n",
+    "y_pred = model.predict(X_test)\n",
+    "mean_absolute_error(y_test, y_pred)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3 (ipykernel)",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}

jrpybestpracccc-0.1.1/jrpybestpracccc/extra_scripts/example_projects/bad_project/setup.cfg

@@ -0,0 +1,7 @@
+[flake8]
+max-line-length = 88
+per-file-ignores = [
+    utils/data/__init__.py:F401,
+    utils/modelling/__init__.py:F401,
+    utils/deployment/__init__.py:F401,
+]

jrpybestpracccc-0.1.1/jrpybestpracccc/extra_scripts/example_projects/good_project/.gitignore

@@ -0,0 +1,3 @@
+*.csv
+*__pycache__/
+