Pandas笔记_python总结笔记

s = pd.Series([1,3,5,np.nan,6,8])

dates = pd.date_range('20170101', periods=6)
df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))

df
Out[4]: 
                   A         B         C         D
2016-10-10  0.630275  1.081899 -1.594402 -2.571683
2016-10-11 -0.211379 -0.166089 -0.480015 -0.346706
2016-10-12 -0.416171 -0.640860  0.944614 -0.756651
2016-10-13  0.652248  0.186364  0.943509  0.053282
2016-10-14 -0.430867 -0.494919 -0.280717 -1.327491
2016-10-15  0.306519 -2.103769 -0.019832  0.035211

df2 = pd.DataFrame({ 'A' : 1.,
                     'B' : pd.Timestamp('20130102'),
                     'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
                     'D' : np.array([3] * 4,dtype='int32'),
                     'E' : pd.Categorical(["test","train","test","train"]),
                     'F' : 'foo' })

Out[20]: 
     A          B    C  D      E    F
0  1.0 2013-01-02  1.0  3   test  foo
1  1.0 2013-01-02  1.0  3  train  foo
2  1.0 2013-01-02  1.0  3   test  foo
3  1.0 2013-01-02  1.0  3  train  foo

import pandas as pd
from datetime import datetime as dt
p1=pd.Timestamp(2017,6,19)
p2=pd.Timestamp(dt(2017,6,19,hour=9,minute=13,second=45))
p3=pd.Timestamp("2017-6-19 9:13:45")

print("type of p1:",type(p1))
print(p1)
print("type of p2:",type(p2))
print(p2)
print("type of p3:",type(p3))
print(p3)


('type of p1:', <class 'pandas.tslib.Timestamp'>)
2017-06-19 00:00:00
('type of p2:', <class 'pandas.tslib.Timestamp'>)
2017-06-19 09:13:45
('type of p3:', <class 'pandas.tslib.Timestamp'>)
2017-06-19 09:13:45

import pandas as pd
from datetime import datetime as dt

p4=pd.to_datetime("2017-6-19 9:13:45")
p5=pd.to_datetime(dt(2017,6,19,hour=9,minute=13,second=45))

print("type of p4:",type(p4))
print(p4)
print("type of p5:",type(p5))
print(p5)

('type of p4:', <class 'pandas.tslib.Timestamp'>)
2017-06-19 09:13:45
('type of p5:', <class 'pandas.tslib.Timestamp'>)
2017-06-19 09:13:45

df = pd.read_csv('x.csv')

import zipfile

with zipfile.ZipFile('x.csv.zip', 'r') as z:
    f = z.open('x.csv')
    df = pd.read_csv(f, header=0)

df2.dtypes

Out[30]: 
A           float64
B    datetime64[ns]
C           float32
D             int32
E          category
F            object
dtype: object

df.head(1)
df.tail(3)

df.index
df.columns
df.values       

df.describe()
Out[19]: 
              A         B         C         D
count  6.000000  6.000000  6.000000  6.000000
mean   0.073711 -0.431125 -0.687758 -0.233103
std    0.843157  0.922818  0.779887  0.973118
min   -0.861849 -2.104569 -1.509059 -1.135632
25%   -0.611510 -0.600794 -1.368714 -1.076610
50%    0.022070 -0.228039 -0.767252 -0.386188
75%    0.658444  0.041933 -0.034326  0.461706
max    1.212112  0.567020  0.276232  1.071804

df.T

df = df.set_index('gpstime')
for index, row in df.iterrows():
    locationF.write("p%s | %s | %s | %s | %s " % (str(cnt), index, str(row[0]), str(row[1]), str(row[2])) + '\n' )

import numpy as np
import pandas as pd

def _map(data, exp):                  
    for index, row in data.iterrows():   # 获取每行的index、row
        for col_name in data.columns:
            row[col_name] = exp(row[col_name]) # 把结果返回给data
    return data

def _1map(data, exp):
    _data = [[exp(row[col_name])               # 把结果转换成2级list
             for col_name in data.columns]
             for index, row in data.iterrows()
            ]
    return _data


if __name__ == "__main__":
    inp = [{
  
  'c1':10, 'c2':100}, {
  
  'c1':11,'c2':110}, {
  
  'c1':12,'c2':120}]
    df = pd.DataFrame(inp)
    temp = _map(df, lambda ele: ele+1 )
    print temp

    _temp = _1map(df, lambda ele: ele+1)
    res_data = pd.DataFrame(_temp)         # 对2级list转换成DataFrame
    print res_data

#对于矩阵，axis=0表示行，1表示列
df.sort_index(axis=1, ascending=False)

df.sort_values(by='B')

import pandas as pd

df = pd.read_csv('./query_result.csv', sep=',')
# 转为日期型
df['gpstime'] = pd.to_datetime(df['gpstime'])
# 按某一列排序
df.sort_values(['gpstime'])

df['A']

df[0:3]
#也可以通过行的索引来选择，但是不能单独写某一行
df['20130102':'20130104']

coords=dftest.as_matrix(columns=['longitude','latitude'])

方法一：直接del DF['column-name']

方法二：采用drop方法，有下面三种等价的表达式： 1. DF= DF.drop('column_name', 1)； 2. DF.drop('column_name',axis=1, inplace=True) # inplace=true表示对原DF操作，否则将结果生成在一个新的DF中 3. DF.drop(DF.columns[ : ], axis=1,inplace=True) # Note: zero indexed 

df = df.set_index('gpstime')
df['2018-04-22 01:00:00': '2018-04-22 05:00:00']

# python2适用
nightdf = nightdf[nightdf['speed']<1]
# python3中的
df06 = df04.loc[True - (float(df04.columns[-6]) > 0.0)]

from sklearn.datasets.samples_generator import make_blobs
from matplotlib import pyplot
from pandas import DataFrame
# generate 2d classification dataset
X, y = make_blobs(n_samples=100, centers=3, n_features=2)
# dict中定义三个key，分别是坐标和label，再通过dict创建DataFrame
df = DataFrame(dict(x=X[:,0], y=X[:,1], label=y))
colors = {
  
  0:'red', 1:'blue', 2:'green'}
fig, ax = pyplot.subplots()
#groupby可以通过传入需要分组的参数实现对数据的分组
grouped = df.groupby('label')
for key, group in grouped:
   group.plot(ax=ax, kind='scatter', x='x', y='y', label=key, color=colors[key])
pyplot.show()

import pandas as pd
import matplotlib.pyplot as plt

# 把数据划分到自定义的区间中
def cla(n,lim):
    return'[%.f,%.f)'%(lim*(n//lim),lim*(n//lim)+lim) # map function

# 默认第一行是标题，从第二行开始是数据。sep是分隔符
df = pd.read_csv('/home/david/iaudience-plan-statistics.csv', sep=',')
# 设置某列的数据类型
df['precent'] = df['precent'].astype('float64')
# 对planid做group，group后对precent做sum
grouped = df['precent'].groupby(df['planid']).sum()

c = pd.DataFrame(grouped)
# 用c.precent或c['precent']都可以
addone = pd.Series([cla(s,1) for s in c.precent])
c['addone'] = addone
groups3 = c.groupby(['addone']).count()
groups3['precent'].plot('bar')
plt.show()

from pandas import Series, DataFrame 

data = DataFrame({'k': [1, 1, 2, 2]}) 

print data 

IsDuplicated = data.duplicated() 

print IsDuplicated  
print type(IsDuplicated) 

data = data.drop_duplicates() 
print data

import pandas as pd
import matplotlib.pyplot as plt
#读取文本数据到DataFrame中，将数据转换为matrix，保存在dataSet中
df = pd.read_table('d:/22.txt')
dataSet = df.as_matrix(columns=None)
# n_clusters=4，参数设置需要的分类这里设置成4类
kmeans = KMeans(n_clusters=4, random_state=0).fit(dataSet)
#center为各类的聚类中心，保存在df_center的DataFrame中给数据加上标签
center = kmeans.cluster_centers_
df_center = pd.DataFrame(center, columns=['x', 'y'])
#标注每个点的聚类结果
labels = kmeans.labels_
#将原始数据中的索引设置成得到的数据类别，根据索引提取各类数据并保存
df = pd.DataFrame(dataSet, index=labels, columns=['x', 'y'])
df1 = df[df.index==0]
df2 = df[df.index==1]
df3 = df[df.index==2]
df4 = df[df.index==3]
#绘图
plt.figure(figsize=(10,8), dpi=80)
axes = plt.subplot()
#s表示点大小，c表示color，marker表示点类型，DataFrame数据列引用参考博客其他文章
type1 = axes.scatter(df1.loc[:,['x']], df1.loc[:,['y']], s=50, c='red', marker='d')
type2 = axes.scatter(df2.loc[:,['x']], df2.loc[:,['y']], s=50, c='green', marker='*')
type3 = axes.scatter(df3.loc[:,['x']], df3.loc[:,['y']], s=50, c='brown', marker='p')
type4 = axes.scatter(df4.loc[:,['x']], df4.loc[:,['y']], s=50, c='black')
#显示聚类中心数据点
type_center = axes.scatter(df_center.loc[:,'x'], df_center.loc[:,'y'], s=40, c='blue')
plt.xlabel('x', fontsize=16)
plt.ylabel('y', fontsize=16)
axes.legend((type1, type2, type3, type4, type_center), ('0','1','2','3','center'), loc=1)
plt.show()

import matplotlib.pyplot as plt
from pandas import DataFrame,Series

Series([4,5,7]).plot()

plt.show() 就可以显示图像了了