[机器学习Day 1~3

数据预处理

第1步：导入库

import numpy as np
import pandas as pd

第2步：导入数据集

//随后一列是label
dataset = pd.read_csv('Data.csv')//读取csv文件
X = dataset.iloc[ : , :-1].values//.iloc[行，列]
Y = dataset.iloc[ : , 3].values  // : 全部行 or 列；[a]第a行 or 列// [a,b,c]第 a,b,c 行 or 列

第3步：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])

第4步：解析分类数据

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_X = LabelEncoder()
X[ : , 0] = labelencoder_X.fit_transform(X[ : , 0])

创建虚拟变量

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

第5步：拆分数据集为训练集合和测试集合

#from sklearn.model_selection import train_test_split
from sklearn.cross_validation import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split( X , Y , test_size = 0.2, random_state = 0)

第6步：特征量化

from sklearn.preprocessing import StandardScaler
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.transform(X_test)

简单线性回归模型

第一步：数据预处理

import pandas as pd
import numpy as np
import matplotlib.pyplot as pltdataset = pd.read_csv('studentscores.csv')
X = dataset.iloc[ : ,   : 1 ].values
Y = dataset.iloc[ : , 1 ].valuesfrom sklearn.model_selection import train_test_split
X_train, X_test, Y_train, Y_test = train_test_split( X, Y, test_size = 1/4, random_state = 0) 

第二步：训练集使用简单线性回归模型来训练

from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor = regressor.fit(X_train, Y_train)

第三步：预测结果

Y_pred = regressor.predict(X_test)

第四步：可视化

训练集结果可视化

plt.scatter(X_train , Y_train, color = 'red')
plt.plot(X_train , regressor.predict(X_train), color ='blue')
plt.show()

测试集结果可视化

plt.scatter(X_test , Y_test, color = 'red')
plt.plot(X_test , regressor.predict(X_test), color ='blue')
plt.show()

多元线性回归

第1步: 数据预处理

导入库

import pandas as pd
import numpy as np

导入数据集

dataset = pd.read_csv('50_Startups.csv')
X = dataset.iloc[ : , :-1].values
Y = dataset.iloc[ : ,  4 ].values

将类别数据数字化

from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder = LabelEncoder()
X[: , 3] = labelencoder.fit_transform(X[ : , 3])
onehotencoder = OneHotEncoder(categorical_features = [3])
X = onehotencoder.fit_transform(X).toarray()

躲避虚拟变量陷阱

X = X[: , 1:]

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)

第2步： 在训练集上训练多元线性回归模型

from sklearn.linear_model import LinearRegression
regressor = LinearRegression()
regressor.fit(X_train, Y_train)

Step 3: 在测试集上预测结果

y_pred = regressor.predict(X_test)