import pandas as pd import numpy as np df = pd.dataframe({'total_bill': [16.99, 10.34, 23.68, 23.68, 24.59], 'tip': [1.01, 1.66, 3.50, 3.31, 3.61], 'sex': ['female', 'male', 'male', 'male', 'female']})
# data type of columns print df.dtypes # indexes print df.index # return pandas.index print df.columns # each row, return array[array] print df.values
print df.loc[1:3, ['total_bill', 'tip']] print df.loc[1:3, 'tip': 'total_bill'] print df.iloc[1:3, [1, 2]] print df.iloc[1:3, 1: 3]
print df.at[3, 'tip'] print df.iat[3, 1]
print df.ix[1:3, [1, 2]] print df.ix[1:3, ['total_bill', 'tip']]
print df[1: 3] print df[['total_bill', 'tip']] # print df[1:2, ['total_bill', 'tip']] # typeerror: unhashable type
df[df[colunm] boolean expr]
,比如:print df[df['sex'] == 'female'] print df[df['total_bill'] > 20] # or print df.query('total_bill > 20')
# and print df[(df['sex'] == 'female') & (df['total_bill'] > 20)] # or print df[(df['sex'] == 'female') | (df['total_bill'] > 20)] # in print df[df['total_bill'].isin([21.01, 23.68, 24.59])] # not print df[-(df['sex'] == 'male')] print df[-df['total_bill'].isin([21.01, 23.68, 24.59])] # string function print df = df[(-df['app'].isin(sys_app)) & (-df.app.str.contains('^微信\d+$'))]
total = df.loc[df['tip'] == 1.66, 'total_bill'].values[0] total = df.get_value(df.loc[df['tip'] == 1.66].index.values[0], 'total_bill')
df.drop_duplicates(subset=['sex'], keep='first', inplace=true)
print df.groupby('sex').size() print df.groupby('sex').count() print df.groupby('sex')['tip'].count()
select sex, max(tip), sum(total_bill) as total from tips_tb group by sex;
print df.groupby('sex').agg({'tip': np.max, 'total_bill': np.sum}) # count(distinct **) print df.groupby('tip').agg({'sex': pd.series.nunique})
# first implementation df.columns = ['total', 'pit', 'xes'] # second implementation df.rename(columns={'total_bill': 'total', 'tip': 'pit', 'sex': 'xes'}, inplace=true)
# 1. df.join(df2, how='left'...) # 2. pd.merge(df1, df2, how='left', left_on='app', right_on='app')
print df.sort_values(['total_bill', 'tip'], ascending=[false, true])
print df.nlargest(3, columns=['total_bill'])
select a.sex, a.tip from tips_tb a where ( select count(*) from tips_tb b where b.sex = a.sex and b.tip > a.tip ) < 2 order by a.sex, a.tip desc;
# 1. df.assign(rn=df.sort_values(['total_bill'], ascending=false) .groupby('sex') .cumcount()+1)\ .query('rn < 3')\ .sort_values(['sex', 'rn']) # 2. df.assign(rn=df.groupby('sex')['total_bill'] .rank(method='first', ascending=false)) \ .query('rn < 3') \ .sort_values(['sex', 'rn'])
# overall replace df.replace(to_replace='female', value='sansa', inplace=true) # dict replace df.replace({'sex': {'female': 'sansa', 'male': 'leone'}}, inplace=true) # replace on where condition df.loc[df.sex == 'male', 'sex'] = 'leone'
print df['tip'].map(lambda x: x - 1) print df[['total_bill', 'tip']].apply(sum) print df.applymap(lambda x: x.upper() if type(x) is str else x)
def chain(current, last): df1 = pd.read_csv(current, names=['app', 'tag', 'uv'], sep='\t') df2 = pd.read_csv(last, names=['app', 'tag', 'uv'], sep='\t') df3 = pd.merge(df1, df2, how='left', on='app') df3['uv_y'] = df3['uv_y'].map(lambda x: 0.0 if pd.isnull(x) else x) df3['growth'] = df3['uv_x'] - df3['uv_y'] return df3[['app', 'growth', 'uv_x', 'uv_y']].sort_values(by='growth', ascending=false)
def difference(left, right, on): """ difference of two dataframes :param left: left dataframe :param right: right dataframe :param on: join key :return: difference dataframe """ df = pd.merge(left, right, how='left', on=on) left_columns = left.columns col_y = df.columns[left_columns.size] df = df[df[col_y].isnull()] df = df.ix[:, 0:left_columns.size] df.columns = left_columns return df
如对本文有疑问, 点击进行留言回复!!
MySQL-关系代数-并、交、差、等值连接、自然连接、左连接。。。
网友评论