read_clean_data.py 文件源码

def rfFitScore(clf, dftrain, dftrain_y, dftest, dftest_y):
    '''random forest classifier fit and score.
       clf=RandomForestClassifier, dftrain=train data,
       dftrain_y=train data Y, dftest=test data,
       dftest_y=test data Y'''

    clfit = clf.fit(dftrain, dftrain_y['Y'])  # clf.fit(X, y)

    imp = clfit.feature_importances_  # ndarray of 562    
    # clfit.fit_transform( X, y=None )  # returns X_new

    new_y = clfit.predict( dftest )  # returns predicted Y

    test_score = clfit.score( dftest, dftest_y['Y'] )
    print("test score:", test_score)  # clfit.oob_score_  
    if (clf.oob_score):
        print("oob score", clfit.oob_score_)

    # calculate test score by other means
    print("predict True %.3f percent, %d out of %d" % \
      ((100 * sum(dftest_y['Y'] == new_y) / dftest_y.shape[0]), \
       sum(dftest_y['Y'] == new_y), dftest_y.shape[0]))
    print("predict False %.3f percent, %d out of %d" % \
      ((100 * sum(dftest_y['Y'] != new_y) / dftest_y.shape[0]), \
       sum(dftest_y['Y'] != new_y), dftest_y.shape[0]))

#    new_p = clfit.predict_proba( dftest )
#    # probability of each X variable to predict each y class
#    print("test predict probabilities head:\n", new_p[:5])

    # cross table of variable predictions
    ptab = pd.crosstab(dftest_y['Y'], new_y, \
        rownames=['actual'], colnames=['predicted'])
    print("cross table:\n", ptab)

    # accuracy: percent labeled correctly
    # precision: true positives / (true positives + true negatives)
    # recall:    true positives / (true positives + false negatives)
    precision, recall, fbeta, support = prfs(dftest_y['Y'], new_y)
    print("precision", precision, "\nrecall", recall, \
        "\nfbeta", fbeta, "\nsupport", support)

    if (clf.oob_score):
        return test_score, imp, clfit.oob_score_
    else:
        return test_score, imp