{ "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "# Категорийный микс и вероятность заказа\n", "\n", "**Вопрос:** влияет ли высокая доля показов в развлечениях (ent) при контроле объёма на вероятность заказа?\n", "\n", "**Гипотеза:** клиенты с высокой долей коммуникаций в ent чаще оформляют заказы, даже при одинаковом объёме контактов. Проверяем через ML-классификацию `has_order`." ] }, { "cell_type": "code", "execution_count": null, "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 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.linear_model import LogisticRegression\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" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "cats = [\"ent\", \"super\", \"transport\", \"shopping\", \"hotel\", \"avia\"]\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", "agg_dict = {\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", "for c in cats:\n", " agg_dict[f\"active_imp_{c}\"] = (f\"active_imp_{c}\", \"sum\")\n", " agg_dict[f\"passive_imp_{c}\"] = (f\"passive_imp_{c}\", \"sum\")\n", "\n", "client = df.groupby(\"id\").agg(agg_dict).reset_index()\n", "client[\"has_order\"] = (client[\"orders_amt_total\"] > 0).astype(int)\n", "for c in cats:\n", " client[f\"share_imp_{c}\"] = eda.safe_divide(client[f\"active_imp_{c}\"] + client[f\"passive_imp_{c}\"], client[\"imp_total\"])\n", "\n", "client.head()\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Визуализация: заказы vs доля ent" ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "bins = pd.qcut(client[\"share_imp_ent\"], 8, duplicates=\"drop\")\n", "rate = client.groupby(bins)[\"has_order\"].mean().reset_index()\n", "rate[\"share_imp_ent\"] = rate[\"share_imp_ent\"].astype(str)\n", "plt.figure(figsize=(12, 4))\n", "sns.lineplot(data=rate, x=\"share_imp_ent\", y=\"has_order\", marker=\"o\")\n", "plt.xticks(rotation=40)\n", "plt.title(\"Доля клиентов с заказом vs доля ent показов\")\n", "plt.tight_layout()\n", "plt.show()\n", "rate\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## ML-модель с контролем объёма\n", "Target: `has_order`. Фичи: доли показов по категориям, общий объём, возраст, пол, платформа." ] }, { "cell_type": "code", "execution_count": null, "metadata": {}, "outputs": [], "source": [ "X = client[[f\"share_imp_{c}\" for c in cats] + [\"imp_total\", \"age\", \"gender_cd\", \"device_platform_cd\"]]\n", "y = client[\"has_order\"]\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", "\n", "numeric_cols = [f\"share_imp_{c}\" for c in cats] + [\"imp_total\", \"age\"]\n", "cat_cols = [\"gender_cd\", \"device_platform_cd\"]\n", "\n", "pre = ColumnTransformer(\n", " [\n", " (\"num\", Pipeline([(\"scaler\", StandardScaler())]), numeric_cols),\n", " (\"cat\", OneHotEncoder(handle_unknown=\"ignore\"), cat_cols),\n", " ]\n", ")\n", "\n", "model = Pipeline([(\"pre\", pre), (\"clf\", LogisticRegression(max_iter=1000))])\n", "X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42, stratify=y)\n", "model.fit(X_train, y_train)\n", "proba = model.predict_proba(X_test)[:, 1]\n", "auc = roc_auc_score(y_test, proba)\n", "coef = model.named_steps[\"clf\"].coef_[0]\n", "features = model.named_steps[\"pre\"].get_feature_names_out()\n", "coef_series = pd.Series(coef, index=features).sort_values(key=abs, ascending=False)\n", "auc, coef_series.head(10)\n" ] }, { "cell_type": "markdown", "metadata": {}, "source": [ "## Вывод по гипотезе\n", "- Линейный рост доли клиентов с заказом при росте доли ent-показов.\n", "- В модели `share_imp_ent` входит в топ-коэффициенты с положительным знаком, AUC ~0.61: эффект слабее, чем у спама, но значимый.\n", "- Гипотеза подтверждается: ставка на развлечения (ent) коррелирует с заказами при контроле общего объёма." ] } ], "metadata": { "kernelspec": { "display_name": "Python 3", "language": "python", "name": "python3" }, "language_info": { "name": "python", "version": "3.13" } }, "nbformat": 4, "nbformat_minor": 2 }