博雅数据机器学习01

博雅数据机器学习01

今天在博雅数据平台上学习观看机器学习的视频

数据预处理

One-hot编码

import pandas as pd

data = pd.read_csv('user_review.csv')

 

# 请在下方作答 #

print(data['User continent'].value_counts(dropna = False))

 

encode_uc = pd.get_dummies(data['User continent'], prefix = 'User continent_')

encode_uc.head()

缺失值填补

import pandas as pd

data = pd.read_csv('user_review.csv')

 

# 请在下方作答 #

print(data['Traveler type'].value_counts(dropna = False))

freq_v = 'Couples'

 

### 缺失值填充

data['Traveler type'] = data['Traveler type'].fillna(freq_v)

 

### 打印

print('')

print(u'缺失值填充完之后：')

print('')

print(data['Traveler type'].value_counts(dropna = False))