D-47-데이터분석

1. pandas merge

• inner

merge_inner = pd.merge(df1, df2)
merge_inner

• outer

merge_outer = pd.merge(df1,df2, how='outer',on='id')
merge_outer

• left

merge_left = pd.merge(df1,df2, how='left', on='name')
merge_left

• right

merge_right = pd.merge(df1, df2, how='right', on='name')
merge_right

2. pandas merge2

merge_df = df1.merge(df2, how='outer', on='id')

3. pandas 데이터 타입 변경

df = df.astype({'col':'datatype'})
df = df.astype({'Age': 'int'})
df = df.astype({'Date': 'datetime64'})
df = df.astype({'Price': 'float'})

4. heatmap

corr_df = df.select_dtypes(include ='int64').corr()

#삼각형 Mask 씌워서 Heatmap 깔끔하게 그려보기
import numpy as np
mask = np.zeros_like(cor_df2, dtype=bool)
mask[np.triu_indices_from(mask)] = True

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
plt.rcParams['figure.figsize'] = [10, 8]

sns.heatmap(corr_df, annot=True, fmt='.1f',cmap='Blues',mask=mask)
plt.title('Annoteat cell with numeric value', fontsize=20)
plt.show()

참고