基於僱員流失率數據進行多分類模型訓練及閾值調整實踐-大數據ML樣本集案例實戰

時間 2019-12-02

標籤基於僱員流失數據進行分類模型訓練閾值調整實踐樣本案例實戰简体版

原文原文鏈接

1 數據的預處理分析

from __future__ import division
import pandas as pd
import numpy as np

churn_df = pd.read_csv('churn.csv')
col_names = churn_df.columns.tolist()

print "Column names:"
print col_names

#前六個後六個
to_show = col_names[:6] + col_names[-6:]

print "\nSample data:"
churn_df[to_show].head(6)
複製代碼

2 數據標準化處理

churn_result = churn_df['Churn?']
y = np.where(churn_result == 'True.',1,0)

# We don't need these columns
to_drop = ['State','Area Code','Phone','Churn?']
churn_feat_space = churn_df.drop(to_drop,axis=1)

# 'yes'/'no' has to be converted to boolean values
# NumPy converts these from boolean to 1. and 0. later
yes_no_cols = ["Int'l Plan","VMail Plan"]
churn_feat_space[yes_no_cols] = churn_feat_space[yes_no_cols] == 'yes'

# Pull out features for future use
features = churn_feat_space.columns

X = churn_feat_space.as_matrix().astype(np.float)

# This is important
from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
X = scaler.fit_transform(X)

print "Feature space holds %d observations and %d features" % X.shape
print "Unique target labels:", np.unique(y)
print X[0]
print len(y[y == 0])

Feature space holds 3333 observations and 17 features
Unique target labels: [0 1]
[ 0.67648946 -0.32758048  1.6170861   1.23488274  1.56676695  0.47664315
  1.56703625 -0.07060962 -0.05594035 -0.07042665  0.86674322 -0.46549436
  0.86602851 -0.08500823 -0.60119509 -0.0856905  -0.42793202]
2850
複製代碼

3 sklearn多模型封裝（已廢棄，學思想）

from sklearn.cross_validation import KFold

def run_cv(X,y,clf_class,**kwargs):
    # Construct a kfolds object
    kf = KFold(len(y),n_folds=5,shuffle=True)
    y_pred = y.copy()

    # Iterate through folds
    for train_index, test_index in kf:
        X_train, X_test = X[train_index], X[test_index]
        y_train = y[train_index]
        # Initialize a classifier with key word arguments
        clf = clf_class(**kwargs)
        clf.fit(X_train,y_train)
        y_pred[test_index] = clf.predict(X_test)
    return y_pred
    
    from sklearn.svm import SVC
    from sklearn.ensemble import RandomForestClassifier as RF
    from sklearn.neighbors import KNeighborsClassifier as KNN
    
    def accuracy(y_true,y_pred):
        # NumPy interprets True and False as 1. and 0.
        return np.mean(y_true == y_pred)
    
    print "Support vector machines:"
    print "%.3f" % accuracy(y, run_cv(X,y,SVC))
    print "Random forest:"
    print "%.3f" % accuracy(y, run_cv(X,y,RF))
    print "K-nearest-neighbors:"
    print "%.3f" % accuracy(y, run_cv(X,y,KNN))
    
    Support vector machines:
    0.916
    Random forest:
    0.944
    K-nearest-neighbors:
    0.893
複製代碼

4 閾值機率調整

def run_prob_cv(X, y, clf_class, **kwargs):
        kf = KFold(len(y), n_folds=5, shuffle=True)
        y_prob = np.zeros((len(y),2))
        for train_index, test_index in kf:
            X_train, X_test = X[train_index], X[test_index]
            y_train = y[train_index]
            clf = clf_class(**kwargs)
            clf.fit(X_train,y_train)
            # Predict probabilities, not classes
            y_prob[test_index] = clf.predict_proba(X_test)
        return y_prob
        
    import warnings
    warnings.filterwarnings('ignore')
    
    # Use 10 estimators so predictions are all multiples of 0.1
    pred_prob = run_prob_cv(X, y, RF, n_estimators=10)
    #print pred_prob[0]
    pred_churn = pred_prob[:,1]
    is_churn = y == 1
    
    # Number of times a predicted probability is assigned to an observation
    counts = pd.value_counts(pred_churn)
    #print counts
    
    # calculate true probabilities
    true_prob = {}
    for prob in counts.index:
        true_prob[prob] = np.mean(is_churn[pred_churn == prob])
        true_prob = pd.Series(true_prob)
    
    # pandas-fu
    counts = pd.concat([counts,true_prob], axis=1).reset_index()
    counts.columns = ['pred_prob', 'count', 'true_prob']
    counts
    
    # 0.7以上流式率達到94%，說明閾值爲0.7是合適的，低於0.7無論，高於0.7的都認爲是流失的
複製代碼