🏠 Pythonで住宅価格を予測するモデルを作ってみた【Kaggle初級】

import pandas as pd

# データの読み込み
train = pd.read_csv('train.csv')
test = pd.read_csv('test.csv')

# データの形状を確認
print(f"訓練データの形状: {train.shape}")
print(f"テストデータの形状: {test.shape}")

# 欠損値の数を確認
missing_values = train.isnull().sum()
missing_values = missing_values[missing_values > 0]
print(missing_values)

# 'MSSubClass'をカテゴリ型に変換
train['MSSubClass'] = train['MSSubClass'].astype(str)
test['MSSubClass'] = test['MSSubClass'].astype(str)

import seaborn as sns
import matplotlib.pyplot as plt

# 数値データの相関係数を計算
corr_matrix = train.corr()
# 相関係数が高い特徴量を表示
top_corr_features = corr_matrix.index[abs(corr_matrix["SalePrice"]) > 0.5]
plt.figure(figsize=(10,10))
sns.heatmap(train[top_corr_features].corr(), annot=True, cmap="RdYlGn")
plt.show()

# 総面積の特徴量を作成
train['TotalSF'] = train['TotalBsmtSF'] + train['1stFlrSF'] + train['2ndFlrSF']
test['TotalSF'] = test['TotalBsmtSF'] + test['1stFlrSF'] + test['2ndFlrSF']

from sklearn.linear_model import LinearRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import mean_squared_error
import numpy as np

# 目的変数と特徴量を定義
X = train.drop(['SalePrice', 'Id'], axis=1)
y = train['SalePrice']

# 訓練データと検証データに分割
X_train, X_valid, y_train, y_valid = train_test_split(X, y, test_size=0.2, random_state=42)

# モデルの訓練
model = LinearRegression()
model.fit(X_train, y_train)

# 検証データで予測
y_pred = model.predict(X_valid)

# RMSEを計算
rmse = np.sqrt(mean_squared_error(y_valid, y_pred))
print(f"RMSE: {rmse}")

# テストデータで予測
test_predictions = model.predict(test.drop('Id', axis=1))

# 提出ファイルの作成
submission = pd.DataFrame({
    'Id': test['Id'],
    'SalePrice': test_predictions
})

# CSVファイルとして保存
submission.to_csv('submission.csv', index=False)