spam hypot

spam_hypot/02_models.ipynb

@@ -0,0 +1,161 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "id": "7254b4c1",
+   "metadata": {},
+   "source": [
+    "# Спам-гипотеза: сравнение моделей\n",
+    "\n",
+    "Target: `high_ctr` (верхний квартиль CTR)."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "c7f54168",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import sqlite3\n",
+    "from pathlib import Path\n",
+    "import sys\n",
+    "import numpy as np\n",
+    "import pandas as pd\n",
+    "import seaborn as sns\n",
+    "import matplotlib.pyplot as plt\n",
+    "from scipy import stats\n",
+    "from sklearn.model_selection import train_test_split\n",
+    "from sklearn.preprocessing import StandardScaler, OneHotEncoder\n",
+    "from sklearn.compose import ColumnTransformer\n",
+    "from sklearn.pipeline import Pipeline\n",
+    "from sklearn.impute import SimpleImputer\n",
+    "from sklearn.metrics import roc_auc_score\n",
+    "\n",
+    "sns.set_theme(style=\"whitegrid\")\n",
+    "plt.rcParams[\"figure.figsize\"] = (10, 5)\n",
+    "\n",
+    "project_root = Path.cwd().resolve()\n",
+    "while not (project_root / \"preanalysis\").exists() and project_root.parent != project_root:\n",
+    "    project_root = project_root.parent\n",
+    "sys.path.append(str(project_root / \"preanalysis\"))\n",
+    "import eda_utils as eda\n",
+    "\n",
+    "db_path = project_root / \"dataset\" / \"ds.sqlite\"\n",
+    "conn = sqlite3.connect(db_path)\n",
+    "df = pd.read_sql_query(\"select * from communications\", conn, parse_dates=[\"business_dt\"])\n",
+    "conn.close()\n",
+    "\n",
+    "for cols, name in [\n",
+    "    (eda.ACTIVE_IMP_COLS, \"active_imp_total\"),\n",
+    "    (eda.PASSIVE_IMP_COLS, \"passive_imp_total\"),\n",
+    "    (eda.ACTIVE_CLICK_COLS, \"active_click_total\"),\n",
+    "    (eda.PASSIVE_CLICK_COLS, \"passive_click_total\"),\n",
+    "    (eda.ORDER_COLS, \"orders_amt_total\"),\n",
+    "]:\n",
+    "    df[name] = df[cols].sum(axis=1)\n",
+    "\n",
+    "df[\"imp_total\"] = df[\"active_imp_total\"] + df[\"passive_imp_total\"]\n",
+    "df[\"click_total\"] = df[\"active_click_total\"] + df[\"passive_click_total\"]\n",
+    "\n",
+    "contact_days = df.groupby(\"id\")[\"business_dt\"].nunique().rename(\"contact_days\")\n",
+    "client = df.groupby(\"id\").agg(\n",
+    "    {\n",
+    "        \"imp_total\": \"sum\",\n",
+    "        \"click_total\": \"sum\",\n",
+    "        \"orders_amt_total\": \"sum\",\n",
+    "        \"age\": \"median\",\n",
+    "        \"gender_cd\": lambda s: s.mode().iat[0],\n",
+    "        \"device_platform_cd\": lambda s: s.mode().iat[0],\n",
+    "    }\n",
+    ").merge(contact_days, on=\"id\", how=\"left\").reset_index()\n",
+    "\n",
+    "client[\"ctr_all\"] = eda.safe_divide(client[\"click_total\"], client[\"imp_total\"])\n",
+    "client[\"cr_click2order\"] = eda.safe_divide(client[\"orders_amt_total\"], client[\"click_total\"])\n",
+    "client[\"avg_imp_per_day\"] = eda.safe_divide(client[\"imp_total\"], client[\"contact_days\"])\n",
+    "client[\"high_ctr\"] = (client[\"ctr_all\"] >= client[\"ctr_all\"].quantile(0.75)).astype(int)\n",
+    "client[\"has_order\"] = (client[\"orders_amt_total\"] > 0).astype(int)\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "21786c63",
+   "metadata": {},
+   "source": [
+    "## Модели: Logistic Regression vs GradientBoosting"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dc8dbc94",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "X = client[[\"avg_imp_per_day\", \"imp_total\", \"click_total\", \"age\", \"gender_cd\", \"device_platform_cd\"]]\n",
+    "X = X.copy()\n",
+    "X[\"gender_cd\"] = eda.normalize_gender(X[\"gender_cd\"])\n",
+    "X[\"device_platform_cd\"] = eda.normalize_device(X[\"device_platform_cd\"])\n",
+    "y = client[\"high_ctr\"]\n",
+    "\n",
+    "num_cols = [\"avg_imp_per_day\", \"imp_total\", \"click_total\", \"age\"]\n",
+    "cat_cols = [\"gender_cd\", \"device_platform_cd\"]\n",
+    "pre = ColumnTransformer([\n",
+    "    (\"num\", Pipeline([(\"imputer\", SimpleImputer(strategy=\"median\")), (\"scaler\", StandardScaler())]), num_cols),\n",
+    "    (\"cat\", OneHotEncoder(handle_unknown=\"ignore\"), cat_cols),\n",
+    "])\n",
+    "\n",
+    "log_reg = Pipeline([(\"pre\", pre), (\"clf\", LogisticRegression(max_iter=1000))])\n",
+    "gb = Pipeline([(\"pre\", pre), (\"clf\", GradientBoostingClassifier(random_state=42))])\n",
+    "\n",
+    "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n",
+    "res = {}\n",
+    "for name, model in [(\"log_reg\", log_reg), (\"gb\", gb)]:\n",
+    "    model.fit(X_train, y_train)\n",
+    "    proba = model.predict_proba(X_test)[:, 1]\n",
+    "    res[name] = roc_auc_score(y_test, proba)\n",
+    "res\n"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "203acf70",
+   "metadata": {},
+   "source": [
+    "## Важности признаков (GradientBoosting)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "3eac9e17",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "gb_model = gb\n",
+    "feat_names = gb_model.named_steps[\"pre\"].get_feature_names_out()\n",
+    "importances = gb_model.named_steps[\"clf\"].feature_importances_\n",
+    "imp_df = pd.DataFrame({\"feature\": feat_names, \"importance\": importances}).sort_values(\"importance\", ascending=False)\n",
+    "plt.figure(figsize=(8, 5))\n",
+    "sns.barplot(data=imp_df.head(15), x=\"importance\", y=\"feature\", palette=\"viridis\")\n",
+    "plt.title(\"Top-15 feature importances (GB)\")\n",
+    "plt.tight_layout()\n",
+    "plt.show()\n",
+    "imp_df.head(15)\n"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "name": "python",
+   "version": "3.13"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}