ワインの品質を予想する

wine_linear_regression.py

import pandas as pd
import matplotlib.pyplot as plt

from sklearn import linear_model

from sklearn.model_selection import train_test_split


def outlier_iqr(df):
    q1 = df.describe().loc['25%']
    q3 = df.describe().loc['75%']
    iqr = q3 - q1

    outlier_min = q1 - (iqr*1.5)
    outlier_max = q3 + (iqr*1.5)

    return df[(df >= outlier_min) & (df <= outlier_max)]\
        .dropna(how='any', axis=0)


def feature_normalize(df):
    return (df - df.mean()) / df.std()


if __name__ == '__main__':
    # Download csv
    csv_url = 'http://archive.ics.uci.edu/ml/machine-learning-databases/wine-quality/winequality-red.csv'
    winequality_red_data = outlier_iqr(pd.read_csv(csv_url, sep=';'))

    X = feature_normalize(
        winequality_red_data.loc[:, [
            'fixed acidity', 'volatile acidity', 'citric acid',
            'residual sugar', 'chlorides', 'free sulfur dioxide',
            'total sulfur dioxide', 'density', 'pH', 'sulphates',
            'alcohol']]).values
    Y = winequality_red_data['quality'].values

    X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.33)

    clf = linear_model.LinearRegression()
    clf.fit(X_train, Y_train)
    Y_pred = clf.predict(X_test)
    print("Score:", clf.score(X_test, Y_test))

    plt.scatter(Y_test, Y_pred)
    plt.xlabel("True Values")
    plt.ylabel("Predictions")
    plt.show()