Question

我有训练和测试数据集。我想对我的测试数据集进行预测并将其保存为CSV。问题是，

我无法保存测试数据集的结果。每次，我都保存Training数据集的结果。

如果你告诉我我失踪的地方那会很棒。

这是我的代码。

import pandas as pd
import numpy as np
from sklearn.ensemble import RandomForestClassifier
import random
from sklearn.metrics import roc_curve
from sklearn.preprocessing import LabelEncoder
from sklearn import metrics

Train = pd.read_csv('Dataset/train.csv', delimiter=';')
Test = pd.read_csv('Dataset/train.csv', delimiter=';')
Train['Type'] = 'Train'  # Create a flag for Train and Test Data set
Test['Type'] = 'Test'
FullData = pd.concat([Train, Test], axis=0)  # Combined both Train and Test Data set

ID_Col = ['USER_ID']  # ID Variables
Target_Col = ["ACTIVITY_DEC_16"]
Cat_Cols = ['ACT_DATE', 'STATUS', 'TP_CURRENT', 'TP_CHANGES_NUM', 'START_PACK', 'OFFER_GROUP', 'BIRTHDAY', 'GENDER',
            'MLLS_STATE',
            'PORTED_IN', 'PORTED_OUT', 'OBLIG_NUM', 'OBLIG_ON_START', 'ASSET_TYPE_LAST', 'DEVICE_TYPE_BUS',
            'USAGE_AREA', 'REFILL_OCT_16', 'REFILL_NOV_16',
            'OUTGOING_OCT_16', 'OUTGOING_NOV_16', 'GPRS_OCT_16', 'GPRS_NOV_16', 'REVENUE_OCT_16',
            'REVENUE_NOV_16']  # Categorical Variables

Num_Cols = list(set(list(FullData.columns)) - set(Cat_Cols) - set(ID_Col) - set(Target_Col))  # Numerical Variables

Other_Col = ['Type']  # Test and Train Data Set Identifier

Num_Cat_Cols = Num_Cols + Cat_Cols  # Combined numerical and Categorical variables

# Create a new variable for each variable having missing value with VariableName_NA
# and flag missing value with 1 and other with 0

for var in Num_Cat_Cols:
    if FullData[var].isnull().any() == True:
        FullData[var + '_NA'] = FullData[var].isnull() * 1

# Impute numercial missing values with mean

FullData[Num_Cols] = FullData[Num_Cols].fillna(FullData[Num_Cols].mean(), inplace=True)
FullData[Cat_Cols] = FullData[Cat_Cols].fillna(value=-9999)

# Create a label encoders for categorical variables and split the data set to train & test. Further split the train data set to Train and Validate

for var in Cat_Cols:
    number = LabelEncoder()
    FullData[var] = number.fit_transform(FullData[var].astype('str'))

# Target Variable is also a categorical so convert it

FullData["ACTIVITY_DEC_16"] = number.fit_transform((FullData["ACTIVITY_DEC_16"].astype('str')))

Train = FullData[FullData['Type'] == 'Train']
Test = FullData[FullData['Type'] == 'Test']

Train['is_train'] = np.random.uniform(0, 1, len(Train)) <= 0.75
Train, Validate = Train[Train['is_train'] == True], Train[Train['is_train'] == False]

Features = list(set(list(FullData.columns)) - set(ID_Col) - set(Target_Col) - set(Other_Col))

X_Train = Train[list(Features)]
Y_Train = Train["ACTIVITY_DEC_16"].values
X_Validate = Validate[list(Features)].values
Y_Validate = Validate["ACTIVITY_DEC_16"].values
X_Test = Test[list(Features)].values

random.seed(100)
rf = RandomForestClassifier(n_estimators=1000)
rf.fit(X_Train, Y_Train)

Status = rf.predict_proba(X_Validate)
fpr, tpr, _ = roc_curve(Y_Validate, Status[:, 1])
roc_auc = metrics.auc(fpr, tpr)

Final_Status = rf.predict_proba(X_Test)
print(Final_Status)
Test['ACTIVITY_DEC_16_PROB'] = Final_Status[:, 1]
Test.to_csv('/Users/isozyesil/PycharmProjects/TaskNo2/Dataset/Output.csv', columns=['USER_ID', 'ACTIVITY_DEC_16_PROB'])

Answer 1

再次到达训练数据而不是测试。

Train = pd.read_csv('Dataset/train.csv', delimiter=';')  
Test = pd.read_csv('Dataset/test.csv', delimiter=';')

预测不同类型的数据集而不是必需的数据集

1 个答案: