pandas 文档自用1

pandas文档

df2[df2['E'].isin(['two', 'four'])]

s1 = pd.Series([1, 2, 3, 4, 5, 6], index=pd.date_range('20130102', periods=6))

df.loc[:, 'D'] = np.array([5] * len(df))

df1 = df.reindex(index=dates[0:4], columns=list(df.columns) + ['E'])

loc可以添加一类修改一列的值，pandas有好多的问题都可以用loc进行处理

df1.loc[dates[0]:dates[1], 'E'] = 1

df1.dropna(how='any')   删除任何缺少数据的行

df1.fillna(value=5)   补全缺失值

 pd.isna(df1)

df.mean()

df.mean(1)

 s.value_counts()

df = pd.DataFrame(np.random.randn(8, 4), columns=['A', 'B', 'C', 'D'])

s = df.iloc[3]

df.append(s, ignore_index=True)   将行添加到数据

df2.stack()

stacked.unstack()

pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])

rng = pd.date_range('1/1/2012', periods=100, freq='S')

ts.resample('5Min').sum()

ts_utc = ts.tz_localize('UTC')   感觉最好不用最好还是加8小时，因为我做的时候有的时间会转换不了

ts_utc.tz_convert('US/Eastern')

ts.to_period()

ps.to_timestamp()

ts.index = (prng.asfreq('M', 'e') + 1).asfreq('H', 's') + 9

df["grade"] = df["raw_grade"].astype("category")

df["grade"].cat.categories = ["very good", "good", "very bad"]

df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium","good", "very good"])

df.sort_values(by="grade")

 df.groupby("grade").size()

a.empty

a.any()

a.all()

df2.A                  df2.bool
df2.abs                df2.boxplot
df2.add                df2.C
df2.add_prefix         df2.clip
df2.add_suffix         df2.clip_lower
df2.align              df2.clip_upper
df2.all                df2.columns
df2.any                df2.combine
df2.append             df2.combine_first
df2.apply              df2.compound
df2.applymap           df2.consolidate
df2.D