机器学习100天（1）

# Step 1: Importing the libraries
import numpy as np
import pandas as pd

# Step 2: Importing dataset
# 读入数据
dataset = pd.read_csv('../datasets/Data.csv')
# 取数据的前三列为X， 最后一列为Y
# iloc[:]：前表示取行，后表示取列
# 对于X就是取所有行，取到第三列（原来放的是-1，不是很理解）
# 对于Y就是取多有行，取第四列
X = dataset.iloc[:, :3].values
Y = dataset.iloc[:, 3].values
print("Step 2: Importing dataset")
print("X")
print(X)
print("Y")
print(Y)

# Step 3: Handling the missing data
from sklearn.preprocessing import Imputer
# 将数据中缺失的值用当前列的平均值填充
imputer = Imputer(missing_values="NaN", strategy="mean", axis=0)
# 匹配所有行，（1,3]列
imputer = imputer.fit(X[:, 1:3])
# 填充
X[:, 1:3] = imputer.transform(X[:, 1:3])
print("---------------------")
print("Step 3: Handling the missing data")
print("step2")
print("X")
print(X)

# Step 4: Encoding categorical data
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
# 连续特征编码
labelencoder_X = LabelEncoder()
＃　取第一列
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
# Creating a dummy variable
＃　离散特征编码　　categorical_features是需要独热编码的列索引
onehotencoder = OneHotEncoder(categorical_features=[0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder()
# fit_transform来学习以及进行编码
Y = labelencoder_Y.fit_transform(Y)
print("---------------------")
print("Step 4: Encoding categorical data")
print("X")
print(X)
print("Y")
print(Y)

# Step 5: Splitting the datasets into training sets and Test sets
from sklearn.model_selection import train_test_split
＃　分离训练集和测试集
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=0)
print("---------------------")
print("Step 5: Splitting the datasets into training sets and Test sets")
print("X_train")
print(X_train)
print("X_test")
print(X_test)
print("Y_train")
print(Y_train)
print("Y_test")
print(Y_test)

# Step 6: Feature Scaling  数据标准化 转化为均值为0 方差为1的数据
from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)
print("---------------------")
print("Step 6: Feature Scaling")
print("X_train")
print(X_train)
print("X_test")
print(X_test)