def process_missing_data(housing):
"""
方法1：去掉对应的数据
方法2：去掉整个属性
方法3：赋值（0，平均值，中位数等）
pandas.DataFrame中的dropna(), drop(), fillna()实现
housing.dropna(subset=["total_bedrooms"]) # 方法1
housing.drop("total_bedrooms", axis=1) # 方法2
median = housing["total_bedrooms"].median() # 计算中位数
housing["total_bedrooms"].fillna(median) # 方法3
scikit-learn中的Imputer
imputer = Imputer(strategy="median")
housing_num = housing.drop("ocean_proximity", axis=1)
imputer.fix(housing_num)
X = imputer.transform(housing_num)
"""
imputer = Imputer(strategy="median")
housing_num = housing.drop("ocean_proximity", axis=1)
imputer.fix(housing_num)
X = imputer.transform(housing_num)
housing_tr = pd.DataFrame(X, columns=housing_num.columns)
def read_data():
dataset = pd.read_csv('/datasets/Data.csv')
X = dataset.iloc[:, :-1].values
Y = dataset.iloc[:, 3].values
imputer = Imputer(missing_values="NaN", strategy="mean", axis=0)
imputer = imputer.fix(X[:, 1:3])
labelencoder_X = LabelEncoder()
X[:, 0] = labelencoder_X.fit_transform(X[:, 0])
onehotencoder = OneHotEncoder(categorical_features=[0])
X = onehotencoder.fit_transform(X).toarray()
labelencoder_Y = LabelEncoder()
Y = labelencoder_Y.fit_transform(Y)
X_train, X_test, Y_train, Y_test = train_test_split(X,
Y,
test_size=0.2,
random_state=0)
sc_X = StandardScaler()
X_train = sc_X.fit_transform(X_train)
X_test = sc_X.fit_transform(X_test)
#Categorical Data
#Importing the libraries
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
#Importing the dataset
dataset = pd.read_csv("Data.csv")
x = dataset.iloc[:, :-1].values
y = dataset.iloc[:, 3].values
#Splitting the dataset into the Trainning set and Test set
from sklearn.preprocessing import Imputer
imputer = Imputer(missing_values="NaN", strategy="mean", axis=0)
imputer = Imputer.fix(x[:, 1:3])
x[:, 1:3] = imputer.transform(x[:, 1:3])
#Encoding Categorical Data
#Encoding the Independent Variable
from sklearn.preprocessing import LabelEncoder, OneHotEncoder
labelencoder_x = LabelEncoder()
x[:, 0] = labelencoder_x.fit_transform(x[:, 0])
onehotencoder = OneHotEncoder(categorical_features=[0])
x = onehotencoder.fit_transform(x).toarray()
#Encoding the Dependent Variable
labelencoder_y = LabelEncoder()
y = labelencoder_y.fit_transform(y)