第1步: 数据预处理
导入库
importpandasaspdimportnumpyasnp
导入数据集
dataset=pd.read_csv('50_Startups.csv')X=dataset.iloc[ : , :-1].valuesY=dataset.iloc[ : ,4].values
将类别数据数字化
fromsklearn.preprocessingimportLabelEncoder, OneHotEncoderlabelencoder=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
fromsklearn.model_selectionimporttrain_test_splitX_train, X_test, Y_train, Y_test=train_test_split(X, Y,test_size=0.2,random_state=)
第2步: 在训练集上训练多元线性回归模型
fromsklearn.linear_modelimportLinearRegressionregressor=LinearRegression()regressor.fit(X_train, Y_train)
Step 3: 在测试集上预测结果
y_pred=regressor.predict(X_test)
◆◆◆◆◆
· 往· 期· 内· 容·
数据:
Country,Age,Salary,Purchased
France,44,72000,No
Spain,27,48000,Yes
Germany,30,54000,No
Spain,38,61000,No
Germany,40,,Yes
France,35,58000,Yes
Spain,,52000,No
France,48,79000,Yes
Germany,50,83000,No
France,37,67000,Yes
代码:
#Day 1: Data Prepocessing
#Step 1: Importing the libraries
importnumpyasnp
importpandasaspd
#Step 2: Importing dataset
dataset=pd.read_csv('../datasets/Data.csv')
X=dataset.iloc[ : , :-1].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
fromsklearn.preprocessingimportImputer
imputer=Imputer(missing_values ="NaN",strategy ="mean",axis =)
imputer=imputer.fit(X[ : , 1:3])
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
fromsklearn.preprocessingimportLabelEncoder, OneHotEncoder
labelencoder_X=LabelEncoder()
X[ : ,]=labelencoder_X.fit_transform(X[ : ,])
#Creating a dummy variable
onehotencoder=OneHotEncoder(categorical_features =[])
X=onehotencoder.fit_transform(X).toarray()
labelencoder_Y=LabelEncoder()
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
fromsklearn.model_selectionimporttrain_test_split
X_train,X_test,Y_train,Y_test=train_test_split(X,Y,test_size=0.2,random_state=)
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
fromsklearn.preprocessingimportStandardScaler
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)
领取专属 10元无门槛券
私享最新 技术干货