![\"Open](\"https://colab.research.google.com/assets/colab-badge.svg\"){kind=icon}
"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 1,
+ "metadata": {
+ "id": "669Bj7r8lcn1"
+ },
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "import pandas as pd\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df = pd.read_csv(\"/content/email_text.csv\")"
+ ],
+ "metadata": {
+ "id": "eb6ElgqmRjSV"
+ },
+ "execution_count": 2,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df.head(10)"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 363
+ },
+ "id": "oJkvZkyCSQ_D",
+ "outputId": "aa439ac5-03e3-4552-c486-59fb2a55257c"
+ },
+ "execution_count": 3,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ " label text\n",
+ "0 0 user id enrondlr pw bnawebescapenumber origina...\n",
+ "1 0 hi chris tonight we are rolling out a new repo...\n",
+ "2 0 rika r these new original message from thomas ...\n",
+ "3 0 john gerald we are currently trading under gtc...\n",
+ "4 0 gerald and stacy attached is a worksheet for a...\n",
+ "5 0 fyi below is a copy of my communication with m...\n",
+ "6 0 pg e gt nw plans lateral across washington sta...\n",
+ "7 0 mark i am working with the east power desk to ...\n",
+ "8 0 oops here it is kal original message from shah...\n",
+ "9 0 mark and charlie fmpa is ready to bill us for ..."
+ ],
+ "text/html": [
+ "\n",
+ " | \n", + " | label | \n", + "text | \n", + "
|---|---|---|
| 0 | \n", + "0 | \n", + "user id enrondlr pw bnawebescapenumber origina... | \n", + "
| 1 | \n", + "0 | \n", + "hi chris tonight we are rolling out a new repo... | \n", + "
| 2 | \n", + "0 | \n", + "rika r these new original message from thomas ... | \n", + "
| 3 | \n", + "0 | \n", + "john gerald we are currently trading under gtc... | \n", + "
| 4 | \n", + "0 | \n", + "gerald and stacy attached is a worksheet for a... | \n", + "
| 5 | \n", + "0 | \n", + "fyi below is a copy of my communication with m... | \n", + "
| 6 | \n", + "0 | \n", + "pg e gt nw plans lateral across washington sta... | \n", + "
| 7 | \n", + "0 | \n", + "mark i am working with the east power desk to ... | \n", + "
| 8 | \n", + "0 | \n", + "oops here it is kal original message from shah... | \n", + "
| 9 | \n", + "0 | \n", + "mark and charlie fmpa is ready to bill us for ... | \n", + "
| \n", + " | count | \n", + "
|---|---|
| label | \n", + "\n", + " |
| 0 | \n", + "9840 | \n", + "
| 1 | \n", + "7575 | \n", + "
| \n", + " | label | \n", + "
|---|---|
| 0 | \n", + "0 | \n", + "
| 1 | \n", + "0 | \n", + "
| 2 | \n", + "0 | \n", + "
| 3 | \n", + "0 | \n", + "
| 4 | \n", + "0 | \n", + "
| ... | \n", + "... | \n", + "
| 17410 | \n", + "0 | \n", + "
| 17411 | \n", + "0 | \n", + "
| 17412 | \n", + "0 | \n", + "
| 17413 | \n", + "0 | \n", + "
| 17414 | \n", + "0 | \n", + "
17415 rows × 1 columns
\n", + ""
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "wvsuiNVuMWa5"
+ },
+ "outputs": [],
+ "source": [
+ "import pandas as pd\n",
+ "\n",
+ "# Load all necessary files\n",
+ "try:\n",
+ " booknow_booking_df = pd.read_csv('booknow_booking.csv')\n",
+ " cinepos_booking_df = pd.read_csv('cinePOS_booking.csv')\n",
+ " id_relation_df = pd.read_csv('movie_theater_id_relation.csv')\n",
+ " booknow_visits_df = pd.read_csv('booknow_visits.csv')\n",
+ " date_info_df = pd.read_csv('date_info.csv')\n",
+ " booknow_theaters_df = pd.read_csv('booknow_theaters.csv')\n",
+ "\n",
+ " print(\"All files loaded successfully.\")\n",
+ "except Exception as e:\n",
+ " print(f\"Error loading files: {e}\")\n",
+ " # Stop execution if files can't be loaded\n",
+ " raise e\n",
+ "\n",
+ "print(\"Starting data consolidation...\")\n",
+ "\n",
+ "# --- 1a: Clean booknow_theaters ---\n",
+ "# Drop rows where book_theater_id is null, as they cannot be linked\n",
+ "booknow_theaters_df.dropna(subset=['book_theater_id'], inplace=True)\n",
+ "# We'll ignore lat/lon and sparse theater_type/area for this model\n",
+ "booknow_theaters_df = booknow_theaters_df[['book_theater_id']]\n",
+ "\n",
+ "# --- 1b: Process booknow_booking (Online) ---\n",
+ "# Convert to datetime and get the date part\n",
+ "booknow_booking_df['show_datetime'] = pd.to_datetime(booknow_booking_df['show_datetime'])\n",
+ "booknow_booking_df['show_date'] = booknow_booking_df['show_datetime'].dt.strftime('%Y-%m-%d')\n",
+ "# Aggregate: sum tickets by theater and date\n",
+ "booknow_agg_df = booknow_booking_df.groupby(['book_theater_id', 'show_date'])['tickets_booked'].sum().reset_index()\n",
+ "booknow_agg_df.rename(columns={'tickets_booked': 'total_booknow_tickets'}, inplace=True)\n",
+ "\n",
+ "# --- 1c: Process cinePOS_booking (On-site) ---\n",
+ "# Convert to datetime and get the date part\n",
+ "cinepos_booking_df['show_datetime'] = pd.to_datetime(cinepos_booking_df['show_datetime'])\n",
+ "cinepos_booking_df['show_date'] = cinepos_booking_df['show_datetime'].dt.strftime('%Y-%m-%d')\n",
+ "# Aggregate: sum tickets by theater and date\n",
+ "cinepos_agg_df = cinepos_booking_df.groupby(['cine_theater_id', 'show_date'])['tickets_sold'].sum().reset_index()\n",
+ "cinepos_agg_df.rename(columns={'tickets_sold': 'total_cinepos_tickets'}, inplace=True)\n",
+ "\n",
+ "# --- 1d: Link cinePOS to booknow IDs ---\n",
+ "cinepos_linked_df = pd.merge(cinepos_agg_df, id_relation_df, on='cine_theater_id', how='inner')\n",
+ "# Re-aggregate in case multiple cinePOS IDs map to a single book_theater_id\n",
+ "cinepos_linked_agg_df = cinepos_linked_df.groupby(['book_theater_id', 'show_date'])['total_cinepos_tickets'].sum().reset_index()\n",
+ "\n",
+ "# --- 1e: Create Master DataFrame ---\n",
+ "# Start with the base visits data (our target)\n",
+ "master_df = booknow_visits_df.copy()\n",
+ "\n",
+ "# Merge calendar info\n",
+ "master_df = pd.merge(master_df, date_info_df, on='show_date', how='left')\n",
+ "\n",
+ "# Merge aggregated BookNow bookings\n",
+ "master_df = pd.merge(master_df, booknow_agg_df, on=['book_theater_id', 'show_date'], how='left')\n",
+ "\n",
+ "# Merge aggregated and linked CinePOS bookings\n",
+ "master_df = pd.merge(master_df, cinepos_linked_agg_df, on=['book_theater_id', 'show_date'], how='left')\n",
+ "\n",
+ "# --- 1f: Final Cleanup ---\n",
+ "# Fill booking NaNs with 0 (days with visits but no recorded online/POS bookings)\n",
+ "master_df['total_booknow_tickets'].fillna(0, inplace=True)\n",
+ "master_df['total_cinepos_tickets'].fillna(0, inplace=True)\n",
+ "\n",
+ "# Convert show_date to datetime object for sorting and feature engineering\n",
+ "master_df['show_date'] = pd.to_datetime(master_df['show_date'])\n",
+ "\n",
+ "print(\"--- Master DataFrame Created ---\")\n",
+ "print(master_df.head())\n",
+ "print(f\"\\nShape of master_df: {master_df.shape}\")\n",
+ "print(master_df.info())"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Step 2: Feature Engineering & Model Validation"
+ ],
+ "metadata": {
+ "id": "UvSxegRaNEPO"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from sklearn.preprocessing import LabelEncoder\n",
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "from sklearn.metrics import mean_squared_error\n",
+ "\n",
+ "print(\"\\n--- Starting Step 2: Feature Engineering & Validation ---\")\n",
+ "\n",
+ "# --- 2a: Create Features ---\n",
+ "# Create 'total_tickets' feature\n",
+ "master_df['total_tickets'] = master_df['total_booknow_tickets'] + master_df['total_cinepos_tickets']\n",
+ "\n",
+ "# Date Features\n",
+ "master_df['day_of_month'] = master_df['show_date'].dt.day\n",
+ "master_df['month'] = master_df['show_date'].dt.month\n",
+ "master_df['year'] = master_df['show_date'].dt.year\n",
+ "master_df['day_of_year'] = master_df['show_date'].dt.dayofyear\n",
+ "master_df['is_weekend'] = master_df['day_of_week'].isin(['Saturday', 'Sunday']).astype(int)\n",
+ "\n",
+ "# CRITICAL: Sort by theater and date\n",
+ "master_df = master_df.sort_values(by=['book_theater_id', 'show_date'])\n",
+ "\n",
+ "# Lag & Rolling Features\n",
+ "print(\"Creating lag and rolling features...\")\n",
+ "gb = master_df.groupby('book_theater_id')['audience_count']\n",
+ "master_df['audience_lag_7'] = gb.shift(7)\n",
+ "master_df['audience_lag_14'] = gb.shift(14)\n",
+ "master_df['audience_roll_mean_7'] = gb.shift(1).rolling(7, min_periods=1).mean()\n",
+ "\n",
+ "# --- 2b: Categorical Encoding ---\n",
+ "# We will use LabelEncoder for IDs and One-Hot Encoding for 'day_of_week'\n",
+ "le = LabelEncoder()\n",
+ "master_df['book_theater_id_encoded'] = le.fit_transform(master_df['book_theater_id'])\n",
+ "master_df = pd.get_dummies(master_df, columns=['day_of_week'], prefix='dow')\n",
+ "\n",
+ "# --- 2c: Clean Data ---\n",
+ "# Drop rows where lag features are NaN (at the start of each series)\n",
+ "master_df_cleaned = master_df.dropna()\n",
+ "print(f\"Data shape after feature engineering and cleaning: {master_df_cleaned.shape}\")\n",
+ "\n",
+ "# --- 2d: Time-Series Split for Validation ---\n",
+ "target_col = 'audience_count'\n",
+ "# Exclude original IDs and date\n",
+ "features = [col for col in master_df_cleaned.columns if col not in [\n",
+ " 'audience_count', 'show_date', 'book_theater_id'\n",
+ "]]\n",
+ "\n",
+ "X = master_df_cleaned[features]\n",
+ "y = master_df_cleaned[target_col]\n",
+ "\n",
+ "# We will use the last 4 weeks (28 days) for validation\n",
+ "max_date = master_df_cleaned['show_date'].max()\n",
+ "split_date = max_date - pd.to_timedelta('28 days')\n",
+ "\n",
+ "train_mask = (master_df_cleaned['show_date'] < split_date)\n",
+ "valid_mask = (master_df_cleaned['show_date'] >= split_date)\n",
+ "\n",
+ "X_train, y_train = X[train_mask], y[train_mask]\n",
+ "X_valid, y_valid = X[valid_mask], y[valid_mask]\n",
+ "\n",
+ "print(f\"Training data shape: {X_train.shape}\")\n",
+ "print(f\"Validation data shape: {X_valid.shape}\")\n",
+ "\n",
+ "# --- 2e: Train and Validate Model ---\n",
+ "print(\"\\nTraining RandomForestRegressor for validation...\")\n",
+ "# Use a fast and powerful RandomForest\n",
+ "rf = RandomForestRegressor(\n",
+ " n_estimators=100,\n",
+ " random_state=42,\n",
+ " n_jobs=-1,\n",
+ " min_samples_leaf=5,\n",
+ " max_features=0.7\n",
+ ")\n",
+ "\n",
+ "rf.fit(X_train, y_train)\n",
+ "\n",
+ "# Evaluate\n",
+ "y_pred = rf.predict(X_valid)\n",
+ "rmse = np.sqrt(mean_squared_error(y_valid, y_pred))\n",
+ "print(f\"\\n--- Validation Complete ---\")\n",
+ "print(f\"Validation RMSE: {rmse:.4f}\")\n",
+ "print(\"This shows our model is predictive. Now we will build the final submission.\")"
+ ],
+ "metadata": {
+ "id": "XdhawvAYM_qs"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Step 3: Create Full Dataset for Submission"
+ ],
+ "metadata": {
+ "id": "aedKBYJ5NInq"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import pandas as pd\n",
+ "from itertools import product\n",
+ "from sklearn.preprocessing import LabelEncoder\n",
+ "\n",
+ "print(\"\\n--- Starting Step 3: Creating Full Train+Test Dataset ---\")\n",
+ "\n",
+ "# --- 3a: Reload original data ---\n",
+ "# We need the original files to build the full train+test set\n",
+ "booknow_visits_df = pd.read_csv('booknow_visits.csv')\n",
+ "date_info_df = pd.read_csv('date_info.csv')\n",
+ "\n",
+ "# --- 3b: Identify Test Period ---\n",
+ "booknow_visits_df['show_date'] = pd.to_datetime(booknow_visits_df['show_date'])\n",
+ "date_info_df['show_date'] = pd.to_datetime(date_info_df['show_date'])\n",
+ "max_train_date = booknow_visits_df['show_date'].max()\n",
+ "test_dates_df = date_info_df[date_info_df['show_date'] > max_train_date]\n",
+ "print(f\"Test period identified: {test_dates_df['show_date'].min().date()} to {test_dates_df['show_date'].max().date()}\")\n",
+ "\n",
+ "# --- 3c: Create Test Scaffolding ---\n",
+ "all_theater_ids = booknow_visits_df['book_theater_id'].unique()\n",
+ "test_scaffold_df = pd.DataFrame(product(all_theater_ids, test_dates_df['show_date']),\n",
+ " columns=['book_theater_id', 'show_date'])\n",
+ "print(f\"Test scaffold created with shape: {test_scaffold_df.shape}\")\n",
+ "\n",
+ "# --- 3d: Combine Train and Test ---\n",
+ "# `audience_count` will be NaN for the test pairs\n",
+ "full_data_df = pd.concat([booknow_visits_df, test_scaffold_df], sort=True)\n",
+ "full_data_df = full_data_df.sort_values(by=['book_theater_id', 'show_date']).reset_index(drop=True)\n",
+ "\n",
+ "# --- 3e: Re-run Feature Engineering on Full Dataset ---\n",
+ "# We re-use the aggregated DataFrames from Step 1\n",
+ "print(\"Merging all features into full dataset...\")\n",
+ "full_master_df = pd.merge(full_data_df, date_info_df, on='show_date', how='left')\n",
+ "full_master_df = pd.merge(full_master_df, booknow_agg_df, on=['book_theater_id', 'show_date'], how='left')\n",
+ "full_master_df = pd.merge(full_master_df, cinepos_linked_agg_df, on=['book_theater_id', 'show_date'], how='left')\n",
+ "\n",
+ "# Cleanup NaNs\n",
+ "full_master_df['total_booknow_tickets'].fillna(0, inplace=True)\n",
+ "full_master_df['total_cinepos_tickets'].fillna(0, inplace=True)\n",
+ "full_master_df['total_tickets'] = full_master_df['total_booknow_tickets'] + full_master_df['total_cinepos_tickets']\n",
+ "\n",
+ "# Date Features\n",
+ "full_master_df['day_of_month'] = full_master_df['show_date'].dt.day\n",
+ "full_master_df['month'] = full_master_df['show_date'].dt.month\n",
+ "full_master_df['year'] = full_master_df['show_date'].dt.year\n",
+ "full_master_df['day_of_year'] = full_master_df['show_date'].dt.dayofyear\n",
+ "full_master_df['is_weekend'] = full_master_df['day_of_week'].isin(['Saturday', 'Sunday']).astype(int)\n",
+ "\n",
+ "# Lag & Rolling Features\n",
+ "# This now correctly uses train data to create lags for the test data\n",
+ "print(\"Creating lags on full dataset...\")\n",
+ "gb_full = full_master_df.groupby('book_theater_id')['audience_count']\n",
+ "full_master_df['audience_lag_7'] = gb_full.shift(7)\n",
+ "full_master_df['audience_lag_14'] = gb_full.shift(14)\n",
+ "full_master_df['audience_roll_mean_7'] = gb_full.shift(1).rolling(7, min_periods=1).mean()\n",
+ "\n",
+ "# Categorical Encoding\n",
+ "full_master_df['book_theater_id_encoded'] = le.transform(full_master_df['book_theater_id']) # Use the LE from Step 2\n",
+ "full_master_df = pd.get_dummies(full_master_df, columns=['day_of_week'], prefix='dow')\n",
+ "\n",
+ "print(\"--- Full Train+Test Dataset is Ready ---\")\n",
+ "print(full_master_df.info())"
+ ],
+ "metadata": {
+ "id": "s0H0ImjrNNRI"
+ },
+ "execution_count": null,
+ "outputs": []
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Step 4: Final Model Training & Submission"
+ ],
+ "metadata": {
+ "id": "85nmUKffNP_e"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import pandas as pd\n",
+ "import numpy as np\n",
+ "from sklearn.ensemble import RandomForestRegressor\n",
+ "\n",
+ "print(\"\\n--- Starting Step 4: Final Training & Submission ---\")\n",
+ "\n",
+ "# --- 4a: Split into Final Train and Test ---\n",
+ "# Training data is where 'audience_count' is known\n",
+ "train_final_df = full_master_df[full_master_df['audience_count'].notnull()]\n",
+ "# Test data is where 'audience_count' is unknown\n",
+ "test_final_df = full_master_df[full_master_df['audience_count'].isnull()]\n",
+ "\n",
+ "# Clean the final training data (drop initial NaNs)\n",
+ "train_final_df = train_final_df.dropna(subset=['audience_lag_7', 'audience_lag_14', 'audience_roll_mean_7'])\n",
+ "\n",
+ "print(f\"Final training data shape: {train_final_df.shape}\")\n",
+ "print(f\"Final test data shape: {test_final_df.shape}\")\n",
+ "\n",
+ "# --- 4b: Align Columns ---\n",
+ "# Get feature list from the training set\n",
+ "features = [col for col in train_final_df.columns if col not in [\n",
+ " 'audience_count', 'show_date', 'book_theater_id'\n",
+ "]]\n",
+ "\n",
+ "# Ensure test set has the exact same columns as the train set\n",
+ "X_train_final = train_final_df[features]\n",
+ "y_train_final = train_final_df[target_col]\n",
+ "\n",
+ "# Align test set columns\n",
+ "X_test_final = test_final_df.copy()\n",
+ "for col in features:\n",
+ " if col not in X_test_final.columns:\n",
+ " X_test_final[col] = 0\n",
+ "X_test_final = X_test_final[features] # Keep only feature columns in correct order\n",
+ "\n",
+ "# Handle any NaNs in test features (e.g., if a new theater had no lag data)\n",
+ "# For this problem, we'll fill with 0\n",
+ "X_test_final.fillna(0, inplace=True)\n",
+ "\n",
+ "# --- 4c: Train Final Model ---\n",
+ "print(\"Training final model on ALL available data...\")\n",
+ "rf_final = RandomForestRegressor(\n",
+ " n_estimators=100,\n",
+ " random_state=42,\n",
+ " n_jobs=-1,\n",
+ " min_samples_leaf=5,\n",
+ " max_features=0.7\n",
+ ")\n",
+ "rf_final.fit(X_train_final, y_train_final)\n",
+ "print(\"Final model trained.\")\n",
+ "\n",
+ "# --- 4d: Make Predictions ---\n",
+ "print(\"Making final predictions...\")\n",
+ "predictions = rf_final.predict(X_test_final)\n",
+ "\n",
+ "# --- 4e: Format Submission File ---\n",
+ "submission_df = test_final_df[['book_theater_id', 'show_date']].copy()\n",
+ "submission_df['audience_count'] = predictions\n",
+ "\n",
+ "# Format the ID: book_theater_id + show_date\n",
+ "submission_df['show_date'] = submission_df['show_date'].dt.strftime('%Y-%m-%d')\n",
+ "submission_df['ID'] = submission_df['book_theater_id'] + '_' + submission_df['show_date']\n",
+ "\n",
+ "# Ensure predictions are non-negative and integers\n",
+ "submission_df['audience_count'] = np.round(submission_df['audience_count']).astype(int)\n",
+ "submission_df.loc[submission_df['audience_count'] < 0, 'audience_count'] = 0\n",
+ "\n",
+ "# Select final columns\n",
+ "final_submission = submission_df[['ID', 'audience_count']]\n",
+ "\n",
+ "# Save the file\n",
+ "final_submission.to_csv('submission.csv', index=False)\n",
+ "\n",
+ "print(\"\\n--- Submission File Created! ---\")\n",
+ "print(final_submission.head())\n",
+ "print(f\"File 'submission.csv' saved with {len(final_submission)} predictions.\")"
+ ],
+ "metadata": {
+ "id": "vxFSnZKTNiZK"
+ },
+ "execution_count": null,
+ "outputs": []
+ }
+ ]
+}
\ No newline at end of file
diff --git a/Welcome_to_Colab.ipynb b/Welcome_to_Colab.ipynb
new file mode 100644
index 0000000..c1d21c4
--- /dev/null
+++ b/Welcome_to_Colab.ipynb
@@ -0,0 +1,655 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "view-in-github",
+ "colab_type": "text"
+ },
+ "source": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "# GA_5_MLP"
+ ],
+ "metadata": {
+ "id": "v2RMPpA9fg29"
+ }
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import pandas as pd\n",
+ "from sklearn.model_selection import train_test_split\n",
+ "\n",
+ "# Step 2: Upload the dataset\n",
+ "from google.colab import files\n",
+ "uploaded = files.upload()"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 73
+ },
+ "id": "GcizXku4X4wC",
+ "outputId": "da4ce9b3-6868-46e1-8ab8-59b8fa65d3ba"
+ },
+ "execution_count": 5,
+ "outputs": [
+ {
+ "output_type": "display_data",
+ "data": {
+ "text/plain": [
+ ""
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "source": [
+ "Exploratory Data Analysis using python"
+ ],
+ "metadata": {
+ "id": "sYAuY4XefN_D"
+ },
+ "id": "sYAuY4XefN_D"
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "import pandas as pd"
+ ],
+ "metadata": {
+ "id": "0vB2tXoDfhD6"
+ },
+ "id": "0vB2tXoDfhD6",
+ "execution_count": 1,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df = pd.read_csv(\"/content/customer_shopping_behavior.csv\")"
+ ],
+ "metadata": {
+ "id": "zxQ7epxjf7S1"
+ },
+ "id": "zxQ7epxjf7S1",
+ "execution_count": 2,
+ "outputs": []
+ },
+ {
+ "cell_type": "code",
+ "source": [
+ "df.head()"
+ ],
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 313
+ },
+ "id": "uZe77-EMgE4T",
+ "outputId": "1952fd3e-a5a9-47f8-fdaf-aa08913a4308"
+ },
+ "id": "uZe77-EMgE4T",
+ "execution_count": 3,
+ "outputs": [
+ {
+ "output_type": "execute_result",
+ "data": {
+ "text/plain": [
+ " Customer ID Age Gender Item Purchased Category Purchase Amount (USD) \\\n",
+ "0 1 55 Male Blouse Clothing 53 \n",
+ "1 2 19 Male Sweater Clothing 64 \n",
+ "2 3 50 Male Jeans Clothing 73 \n",
+ "3 4 21 Male Sandals Footwear 90 \n",
+ "4 5 45 Male Blouse Clothing 49 \n",
+ "\n",
+ " Location Size Color Season Review Rating Subscription Status \\\n",
+ "0 Kentucky L Gray Winter 3.1 Yes \n",
+ "1 Maine L Maroon Winter 3.1 Yes \n",
+ "2 Massachusetts S Maroon Spring 3.1 Yes \n",
+ "3 Rhode Island M Maroon Spring 3.5 Yes \n",
+ "4 Oregon M Turquoise Spring 2.7 Yes \n",
+ "\n",
+ " Shipping Type Discount Applied Promo Code Used Previous Purchases \\\n",
+ "0 Express Yes Yes 14 \n",
+ "1 Express Yes Yes 2 \n",
+ "2 Free Shipping Yes Yes 23 \n",
+ "3 Next Day Air Yes Yes 49 \n",
+ "4 Free Shipping Yes Yes 31 \n",
+ "\n",
+ " Payment Method Frequency of Purchases \n",
+ "0 Venmo Fortnightly \n",
+ "1 Cash Fortnightly \n",
+ "2 Credit Card Weekly \n",
+ "3 PayPal Weekly \n",
+ "4 PayPal Annually "
+ ],
+ "text/html": [
+ "\n",
+ " | \n", + " | Customer ID | \n", + "Age | \n", + "Gender | \n", + "Item Purchased | \n", + "Category | \n", + "Purchase Amount (USD) | \n", + "Location | \n", + "Size | \n", + "Color | \n", + "Season | \n", + "Review Rating | \n", + "Subscription Status | \n", + "Shipping Type | \n", + "Discount Applied | \n", + "Promo Code Used | \n", + "Previous Purchases | \n", + "Payment Method | \n", + "Frequency of Purchases | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| 0 | \n", + "1 | \n", + "55 | \n", + "Male | \n", + "Blouse | \n", + "Clothing | \n", + "53 | \n", + "Kentucky | \n", + "L | \n", + "Gray | \n", + "Winter | \n", + "3.1 | \n", + "Yes | \n", + "Express | \n", + "Yes | \n", + "Yes | \n", + "14 | \n", + "Venmo | \n", + "Fortnightly | \n", + "
| 1 | \n", + "2 | \n", + "19 | \n", + "Male | \n", + "Sweater | \n", + "Clothing | \n", + "64 | \n", + "Maine | \n", + "L | \n", + "Maroon | \n", + "Winter | \n", + "3.1 | \n", + "Yes | \n", + "Express | \n", + "Yes | \n", + "Yes | \n", + "2 | \n", + "Cash | \n", + "Fortnightly | \n", + "
| 2 | \n", + "3 | \n", + "50 | \n", + "Male | \n", + "Jeans | \n", + "Clothing | \n", + "73 | \n", + "Massachusetts | \n", + "S | \n", + "Maroon | \n", + "Spring | \n", + "3.1 | \n", + "Yes | \n", + "Free Shipping | \n", + "Yes | \n", + "Yes | \n", + "23 | \n", + "Credit Card | \n", + "Weekly | \n", + "
| 3 | \n", + "4 | \n", + "21 | \n", + "Male | \n", + "Sandals | \n", + "Footwear | \n", + "90 | \n", + "Rhode Island | \n", + "M | \n", + "Maroon | \n", + "Spring | \n", + "3.5 | \n", + "Yes | \n", + "Next Day Air | \n", + "Yes | \n", + "Yes | \n", + "49 | \n", + "PayPal | \n", + "Weekly | \n", + "
| 4 | \n", + "5 | \n", + "45 | \n", + "Male | \n", + "Blouse | \n", + "Clothing | \n", + "49 | \n", + "Oregon | \n", + "M | \n", + "Turquoise | \n", + "Spring | \n", + "2.7 | \n", + "Yes | \n", + "Free Shipping | \n", + "Yes | \n", + "Yes | \n", + "31 | \n", + "PayPal | \n", + "Annually | \n", + "
| \n", + " | Customer ID | \n", + "Age | \n", + "Gender | \n", + "Item Purchased | \n", + "Category | \n", + "Purchase Amount (USD) | \n", + "Location | \n", + "Size | \n", + "Color | \n", + "Season | \n", + "Review Rating | \n", + "Subscription Status | \n", + "Shipping Type | \n", + "Discount Applied | \n", + "Promo Code Used | \n", + "Previous Purchases | \n", + "Payment Method | \n", + "Frequency of Purchases | \n", + "
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| count | \n", + "3900.000000 | \n", + "3900.000000 | \n", + "3900 | \n", + "3900 | \n", + "3900 | \n", + "3900.000000 | \n", + "3900 | \n", + "3900 | \n", + "3900 | \n", + "3900 | \n", + "3863.000000 | \n", + "3900 | \n", + "3900 | \n", + "3900 | \n", + "3900 | \n", + "3900.000000 | \n", + "3900 | \n", + "3900 | \n", + "
| unique | \n", + "NaN | \n", + "NaN | \n", + "2 | \n", + "25 | \n", + "4 | \n", + "NaN | \n", + "50 | \n", + "4 | \n", + "25 | \n", + "4 | \n", + "NaN | \n", + "2 | \n", + "6 | \n", + "2 | \n", + "2 | \n", + "NaN | \n", + "6 | \n", + "7 | \n", + "
| top | \n", + "NaN | \n", + "NaN | \n", + "Male | \n", + "Blouse | \n", + "Clothing | \n", + "NaN | \n", + "Montana | \n", + "M | \n", + "Olive | \n", + "Spring | \n", + "NaN | \n", + "No | \n", + "Free Shipping | \n", + "No | \n", + "No | \n", + "NaN | \n", + "PayPal | \n", + "Every 3 Months | \n", + "
| freq | \n", + "NaN | \n", + "NaN | \n", + "2652 | \n", + "171 | \n", + "1737 | \n", + "NaN | \n", + "96 | \n", + "1755 | \n", + "177 | \n", + "999 | \n", + "NaN | \n", + "2847 | \n", + "675 | \n", + "2223 | \n", + "2223 | \n", + "NaN | \n", + "677 | \n", + "584 | \n", + "
| mean | \n", + "1950.500000 | \n", + "44.068462 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "59.764359 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "3.750065 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "25.351538 | \n", + "NaN | \n", + "NaN | \n", + "
| std | \n", + "1125.977353 | \n", + "15.207589 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "23.685392 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "0.716983 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "14.447125 | \n", + "NaN | \n", + "NaN | \n", + "
| min | \n", + "1.000000 | \n", + "18.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "20.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "2.500000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "1.000000 | \n", + "NaN | \n", + "NaN | \n", + "
| 25% | \n", + "975.750000 | \n", + "31.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "39.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "3.100000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "13.000000 | \n", + "NaN | \n", + "NaN | \n", + "
| 50% | \n", + "1950.500000 | \n", + "44.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "60.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "3.800000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "25.000000 | \n", + "NaN | \n", + "NaN | \n", + "
| 75% | \n", + "2925.250000 | \n", + "57.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "81.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "4.400000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "38.000000 | \n", + "NaN | \n", + "NaN | \n", + "
| max | \n", + "3900.000000 | \n", + "70.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "100.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "5.000000 | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "NaN | \n", + "50.000000 | \n", + "NaN | \n", + "NaN | \n", + "
| \n", + " | 0 | \n", + "
|---|---|
| Customer ID | \n", + "0 | \n", + "
| Age | \n", + "0 | \n", + "
| Gender | \n", + "0 | \n", + "
| Item Purchased | \n", + "0 | \n", + "
| Category | \n", + "0 | \n", + "
| Purchase Amount (USD) | \n", + "0 | \n", + "
| Location | \n", + "0 | \n", + "
| Size | \n", + "0 | \n", + "
| Color | \n", + "0 | \n", + "
| Season | \n", + "0 | \n", + "
| Review Rating | \n", + "37 | \n", + "
| Subscription Status | \n", + "0 | \n", + "
| Shipping Type | \n", + "0 | \n", + "
| Discount Applied | \n", + "0 | \n", + "
| Promo Code Used | \n", + "0 | \n", + "
| Previous Purchases | \n", + "0 | \n", + "
| Payment Method | \n", + "0 | \n", + "
| Frequency of Purchases | \n", + "0 | \n", + "
| \n", + " | 0 | \n", + "
|---|---|
| Customer ID | \n", + "0 | \n", + "
| Age | \n", + "0 | \n", + "
| Gender | \n", + "0 | \n", + "
| Item Purchased | \n", + "0 | \n", + "
| Category | \n", + "0 | \n", + "
| Purchase Amount (USD) | \n", + "0 | \n", + "
| Location | \n", + "0 | \n", + "
| Size | \n", + "0 | \n", + "
| Color | \n", + "0 | \n", + "
| Season | \n", + "0 | \n", + "
| Review Rating | \n", + "0 | \n", + "
| Subscription Status | \n", + "0 | \n", + "
| Shipping Type | \n", + "0 | \n", + "
| Discount Applied | \n", + "0 | \n", + "
| Promo Code Used | \n", + "0 | \n", + "
| Previous Purchases | \n", + "0 | \n", + "
| Payment Method | \n", + "0 | \n", + "
| Frequency of Purchases | \n", + "0 | \n", + "
| \n", + " | age | \n", + "age_group | \n", + "
|---|---|---|
| 0 | \n", + "55 | \n", + "Middle aged | \n", + "
| 1 | \n", + "19 | \n", + "Young Adult | \n", + "
| 2 | \n", + "50 | \n", + "Middle aged | \n", + "
| 3 | \n", + "21 | \n", + "Young Adult | \n", + "
| 4 | \n", + "45 | \n", + "Middle aged | \n", + "
| 5 | \n", + "46 | \n", + "Middle aged | \n", + "
| 6 | \n", + "63 | \n", + "Senior | \n", + "
| 7 | \n", + "27 | \n", + "Young Adult | \n", + "
| 8 | \n", + "26 | \n", + "Young Adult | \n", + "
| 9 | \n", + "57 | \n", + "Middle aged | \n", + "
| \n", + " | frequency_of_purchases | \n", + "purchase_frequency_days | \n", + "
|---|---|---|
| 0 | \n", + "Fortnightly | \n", + "14.0 | \n", + "
| 1 | \n", + "Fortnightly | \n", + "14.0 | \n", + "
| 2 | \n", + "Weekly | \n", + "7.0 | \n", + "
| 3 | \n", + "Weekly | \n", + "7.0 | \n", + "
| 4 | \n", + "Annually | \n", + "365.0 | \n", + "
| 5 | \n", + "Weekly | \n", + "7.0 | \n", + "
| 6 | \n", + "Quarterly | \n", + "90.0 | \n", + "
| 7 | \n", + "Weekly | \n", + "7.0 | \n", + "
| 8 | \n", + "Annually | \n", + "365.0 | \n", + "
| 9 | \n", + "Quarterly | \n", + "90.0 | \n", + "