[数据分析]Pandas自测20题

data = {"grammer":["Python","C","Java","GO",np.nan,"SQL","PHP","Python"],
       "score":[1,2,np.nan,4,5,6,7,10]}

df = pd.DataFrame(data)

grammer  score
0 Python    1.0
7 Python   10.0

result=df[df['grammer'].str.contains("Python")]

Index(['grammer', 'score'], dtype='object')

df.columns

df.rename(columns={'score':'popularity'}, inplace = True)

df['grammer'].value_counts()

df['popularity'] = df['popularity'].fillna(df['popularity'].interpolate())

df[df['popularity'] > 3]

df.drop_duplicates(['grammer'])

df['popularity'].mean()

df['grammer'].to_list()

df.to_excel('filename.xlsx')

df.shape

df[(df['popularity'] > 3) & (df['popularity'] < 7)]

temp = df['popularity']
df.drop(labels=['popularity'], axis=1,inplace = True)
df.insert(0, 'popularity', temp)

df[df['popularity'] == df['popularity'].max()]

df.tail()

df = df.drop(labels=0)

row={'grammer':'Perl','popularity':6.6}
df = df.append(row,ignore_index=True)

df.sort_values("popularity",inplace=True)

df['grammer'].map(lambda x: len(x))