Question

我正在尝试使用不同的分类器训练模型。并希望在csv文件中保存每个分类器分类报告以获取类的分数值。但是当我尝试执行此操作时，出现以下错误。我真的很感激，如果有人可以帮我解决这个问题，我可以单独测试每个分类器并保存到文件。但它会增加我真正不想要的代码。

raise ValueError("Mix type of y not allowed, got types %s" % ys_types)
ValueError: Mix type of y not allowed, got types {'multiclass', 'continuous- 
multioutput'}

**this is the code am trying with:**
from sklearn.metrics import accuracy_score, log_loss
from sklearn.neighbors import KNeighborsClassifier
from sklearn.tree import DecisionTreeClassifier
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, 
GradientBoostingClassifier
from sklearn.naive_bayes import GaussianNB
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis

将pandas导入为pd

，电话，BASE_ID，CELL_ID，ULTraffic，TCPSYNAtteDelay，日期

1,13548599180,54,251,469,28,20160718034300.0 2,13548599180,1,46,1273,31,20160725023800.0 3,13548599180,54,251,1273,25,20160714012400.0 4,13548599180,54,251,1273,31,20160714085200.0 5,13548599180,54,251,1273,31,20160718034200.0 6,13548599180,54,251,1273,25,20160713082200.0 7,13548599180,54,251,2373,33,20160713091800.0 8,13548599180,54,251,2373,33,20160713091800.0 9,13548599180,54,251,639,31,20160714015300.0 10,13548599180,92,278,690,28,20160704010900.0 11,13548599180,92,278,693,28,20160704010900.0 12,13548599180,92,278,689,31,20160704010900.0 13,13548599180,92,278,1060,25,20160704010900.0 14,13548599180,54,251,1339,29,20160713091500.0 15,13548599180,54,251,1202,29,20160713091500.0 16,13548599180,54,251,975,26,20160713091500.0 17,13548599180,54,251,745,29,20160714015300.0 18,13548599180,54,251,707,27,20160714015300.0

url = 'path\stackflow_sample.csv'
names = ['Phone','Base_ID', 'Cell_ID', 'ULTraffic', 
'TCPSYNAtteDelay','date']

data = pd.read_csv(url, names=names,low_memory=False)
a=data.loc[:,('Phone','Base_ID', 'Cell_ID', 'ULTraffic',         
'TCPSYNAtteDelay','date')]
data_dia = a.Phone ; x_1 = a.drop('Phone',axis = 1 )
x_train, x_test, y_train, y_test = train_test_split(x_1, data_dia, 
test_size=0.3, random_state=42)



classifiers = [
KNeighborsClassifier(3)]
DecisionTreeClassifier()
RandomForestClassifier(),
AdaBoostClassifier(),
GradientBoostingClassifier(),
GaussianNB(),
LinearDiscriminantAnalysis()]

# Logging for Visual Comparison
log_cols = ["Classifier", "Accuracy", "Log Loss"]
log = pd.DataFrame(columns=log_cols)

     for clf in classifiers:
         clf.fit(x_train, y_train)
         name = clf.__class__.__name__

        print("=" * 30)
        print(name)

        print('****Results****')
        train_predictions = clf.predict(x_test)
        acc = accuracy_score(y_test, train_predictions)
        print("Accuracy: {:.4%}".format(acc))

        train_predictions = clf.predict_proba(x_test)
        ll = log_loss(y_test, train_predictions)
        print("Log Loss: {}".format(ll))

        log_entry = pd.DataFrame([[name, acc * 100, ll]], columns=log_cols)
        log = log.append(log_entry)
        report = classification_report(y_test, train_predictions)
    print("log:",log)
    print("=" * 30)

**This is the function am using to save classification_report results of 
classifiers in other file func.py **


def classifaction_report_csv(report):
    report_data = []
    lines = report.split('\n')
    for line in lines[2:-3]:
        row = {}
        row_data = line.split('      ')
        row['class'] = row_data[0]
        row['precision'] = float(row_data[1])
        row['recall'] = float(row_data[2])
        row['f1_score'] = float(row_data[3])
        row['support'] = float(row_data[4])
        report_data.append(row)
    dataframe = pd.DataFrame.from_dict(report_data)
    dataframe.to_csv('classification_report.csv', index = False)

如何在python中为每个分类器保存classification_report结果循环

将pandas导入为pd

0 个答案: