2.1.13.2.KNN with Python

1. 匯入基本的library

• pandas, numpy, matplotlib, seaborn

    import pandas as pd
    import numpy as np
    import matplotlib.pyplot as plt
    import seaborn as sns

• 將圖表直接嵌入到Notebook之中

    %matplotlib inline

2.讀取資料並了解資料

df = pd.read_csv('Classified Data', index_col = 0)
df.head()

3.標準化資料

• 變數的scale通常對結果有很大的影響, 當使用KNN classifier時通常會統一observation的尺度

• 使用StandardScaler

  • StandardScaler的作用是將數據減去平均值並除以方差, 公式為(X-mean)/std

  • 將原始資料的TARGET CLASS drop掉後fit, 再transform

    from sklearn.preprocessing import StandardScaler
    scaler  = StandardScaler()
    scaler.fit(df.drop("TARGET CLASS", axis = 1))
    scaled_features = scaler.transform(df.drop("TARGET CLASS", axis = 1))

• 將標準化後的資料準轉成DataFrame

    df_feat = pd.DataFrame(scaled_features, columns = df.columns[:-1])
    df_feat.head()

4.使用Skikit-learn library

• 首先介紹train_test_split, 這個函式可以隨機劃分訓練集和測試集

    from sklearn.cross_validation import train_test_split
    X = df_feat
    Y = df["TARGET CLASS"]
    X_train, X_test, y_train, y_test = train_test_split(X, Y, test_size=0.4, random_state=101)

5.使用KNN classifier進行預測

• 設定n_neighbors(K)為1

    from sklearn.neighbors import KNeighborsClassifier
    knn = KNeighborsClassifier(n_neighbors = 1)
    knn.fit(X_train, y_train)
    predictions = knn.predict(X_test)

6.評估模型的精度

• 使用classification_report

    from sklearn.metrics import classification_report
    print(classification_report(y_test, predictions))

  
• confusion_matrix

    from sklearn.metrics import confusion_matrix
    print(confusion_matrix(y_test, predictions))

  

7.調整K值

• 將多次的預測值與y_test的差異矩陣取平均

    error_rate = []
    for i in range(1, 40):
        knn = KNeighborsClassifier(n_neighbors = i)
        knn.fit(X_train, y_train)
        pred_i = knn.predict(X_test)
        error_rate.append(np.mean(pred_i != y_test))
  
    plt.figure(figsize = (10, 6))
    plt.plot(range(1,40), error_rate, color = 'blue',linestyle = 'dashed', marker = 'o', markerfacecolor = 'red'
         , markersize = 10)
    plt.title("Error Rate vs K value")
    plt.xlabel('K')

  
• 重新預估k值

    knn = KNeighborsClassifier(n_neighbors = 37)
    knn.fit(X_train, y_train)
    predictions = knn.predict(X_test)
    print(classification_report(y_test, predictions))
    print(confusion_matrix(y_test, predictions))