计数
s = pd.Series(np.random.randint(0, 7, size=10)) s.value_counts()
把数据拼接起来
df = pd.DataFrame(np.random.randn(10, 4)) pieces = [df[:3], df[3:7], df[7:]] pd.concat(pieces)
Join ( left, right, inner, outer )
http://pandas.pydata.org/pandas-docs/stable/merging.html#merging-join
left = pd.DataFrame({'key' : ['foo', 'foo'], 'lval' : [1, 2]})
right = pd.DataFrame({'key' : ['foo', 'foo'], 'rval' : [4, 5]})print leftprint right
pd.merge(left, right, on='key')分组统计 groupby
df = pd.DataFrame({'A' : ['foo', 'bar', 'foo', 'bar', 'foo', 'bar', 'foo', 'bar'], 'B' : ['one', 'one', 'two', 'three', 'two', 'two', 'one', 'three'], 'C' : np.random.randn(8), 'D' : np.random.randn(8)})print dfprint df.groupby(['A', 'B']).sum()Pivot table
df = pd.DataFrame({'A' : ['one', 'one', 'two', 'three'] * 3, 'B' : ['A', 'B', 'C'] * 4, 'C' : ['foo', 'foo', 'foo', 'bar', 'bar', 'bar'] * 2, 'D': np.random.randn(12), 'E' : np.random.randn(12)})
pd.pivot_table(df, values='D', index=['A', 'B'], columns=['C'])生成时间序列
# freq='S' 秒的递进rng = pd.date_range('1/1/2012', periods=100, freq='S')print rng[:5]
ts = pd.Series(np.random.randint(0, 500, len(rng)), index=rng)print ts.head()给数据加类别标签
df = pd.DataFrame({'id':[1,2,3,4,5,6],
"raw_grade":['a', 'b', 'b', 'a', 'a', 'e']})
df["grade"] = df["raw_grade"].astype("category")print df
df["grade"].cat.categories = ["very good", "good", "very bad"]
df["grade"] = df["grade"].cat.set_categories(["very bad", "bad", "medium ", "good", "very good"])print dfprint df.groupby("grade").size()画图
ts = pd.Series(np.random.randn(1000), index=pd.date_range('1/1/2000', periods=1000))
df = pd.DataFrame(np.random.randn(1000, 4), index=ts.index,
columns=['A', 'B', 'C', 'D'])
df = df.cumsum()
plt.figure(); df.plot(); plt.legend(loc='best')读取写入 csv，excel 文件
df.to_csv('foo.csv')
pd.read_csv('foo.csv')
df.to_excel('foo.xlsx', sheet_name='Sheet1')
pd.read_excel('foo.xlsx', 'Sheet1', index_col=None, na_values=['NA'])