# first step [导入库]
import numpy as np
import pandas as pd

# second step [导入数据集]
dataset = pd.read_csv('dataset/1.csv')
X = dataset.iloc[:, :-1].values;
Y = dataset.iloc[:, 3].values;

#print(dataset)
#print(X)
#print(Y)
#print(dataset.iloc[:1].values)

# thrid step [用均值或中值处理丢失数据]
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values="NaN",strategy="mean",axis=0)
imputer = imputer.fit(X[:, 1:3])
X[:, 1:3] = imputer.transform(X[:, 1:3])

#print(X[:, 1:3])

# fourth step [标签类转化为可计算类，数据解析]
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])

#print(X[:, 0])

onehotencoder = OneHotEncoder(categorical_features=[0])
X = onehotencoder.fit_transform(X).toarray()

#print(onehotencoder.fit_transform(X))

labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)

#print(X)
#print(Y)

# fifth step [拆分数据集为训练集和测试集]
from sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size = 0.2, random_state = 0)

print(X_train, X_test, Y_train, Y_test)

# sixth step [特征缩放，采用特征标准化或Z值归一化解决]
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.fit_transform(X_test)

print(X_train)
print(X_test)