机器学习训练营:Task04快来一起挖掘幸福感
数据分析
train_abbr = pd.read_csv(‘data/happiness_train_abbr.csv’)
train_abbr.describe()
8000 rows × 42 columns
test_abbr = pd.read_csv(‘data/happiness_test_abbr.csv’)
test_abbr.head()
2968 rows × 41 columns
#不同幸福感分布情况
train_abbr[‘happiness’].value_counts().plot.pie()
#不同性别幸福感分布情况
import seaborn as sns
sns.countplot(‘gender’,hue= ‘happiness’,data=train_abbr)
df_all = pd.concat((train_abbr,test_abbr),axis=0)
#处理缺失值-查看缺失值
total =df_all.isnull().sum().sort_values(ascending=False)
percent= (df_all.isnull().sum()/df_all.isnull().count()).sort_values(ascending=False)
missing_data= pd.concat([total,percent],axis=1,keys=[‘total’,‘percent’])
missing_data[missing_data[‘percent’]>0]