DAY 5 超大力王爱学Python

1.离散特征的独热编码

先按照示例代码过一遍，然后完成下列题目

现在在py文件中 一次性处理data数据中所有的连续变量和离散变量

• 读取data数据

• import pandas as pd
  data = pd.read_csv('data.csv') 
  data.columns # 看列
  
  for discrete_features in data.columns: 
      if data[discrete_features].dtype =='object': 
          print(discrete_features)

对离散变量进行one-hot编码

data = pd.get_dummies(data,columns=['Home Ownership'])
data.columns

# 读取数据
data = pd.read_csv('data.csv')
# 找到离散变量
discrete_lists=[] # 存放离散变量
for discrete_features in data.columns:
    if data[discrete_features].dtype == 'object':
        discrete_lists.append(discrete_features)
        
data = pd.get_dummies(data,columns= discrete_lists,drop_first = True)
 
data.columns

对独热编码后的变量转化为int类型

data2 = pd.read_csv('data.csv')
list_final = []
for i in data.columns:
    if i not in data2.columns:
        list_final.append(i)
list_final

# 类型转换
for i in list_final:
    data[i] = data[i].astype(int)
data.head()

对所有缺失值进行填充

for i in data.columns:
    if data[i].isnull().sum()>0:
        mean_value = data[i].mean()
        data[i].fillna(mean_value,inplace = True)
        
data.isnull().sum()

@浙大疏锦行