数据分析知识点

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

import matplotlib.pyplot as plt
%matplotlib inline

np.arange(2010,2018,1)

s = Series(index = np.arange(2010,2018,1),data = [100,110,90,300,700,2000,5000,10000])

s.plot()

x = np.arange(-np.pi,np.pi,0.1)
y = np.sin(x) + 2*np.cos(x)
s1 = Series(index=x,data=y)
s1.plot(kind='line')

columns = ['dancer','lucy','mery']
index = ['first','second','third','fouth']
data = np.random.randint(0,150,size=(4,3))
df = DataFrame(data=data,index=index,columns=columns)
df.plot()

score = pd.read_excel('score.xls')
# 版面的绘制
score.plot()
# 图片保存

s = Series(index=['dancer','mery','lucy'],data=[100,98,60])
s.plot(kind='bar')

data = np.random.randint(0,100,size=(5,3))
index = list('ABCDE')
columns = ['python','java','php']
df = DataFrame(data=data,index=index,columns=columns)
df.plot(kind='bar')

df.plot(kind='barh')

s.plot(kind='barh')

tips = pd.read_csv('tips.csv')
tips

# 把一列变成索引
data = tips.set_index('day')
# 把索引变成列
# tips.reset_index()

data.plot(kind='bar')

# 计算每一行的和
index_sum = data.sum(axis=1)

# 计算每天每种聚会人数所占比例
result = data.div(index_sum,axis=0)
result.plot(kind='bar')

s = Series(data = [1,2,1,1,3,5,6,7,9,9])
# 直方图会受到bins（数据分区的个数）影响很大
# 设置normed参数为True，直方图表示的是每一个数出现的概率
s.plot(kind='hist',bins=3,normed=True)
# 为了避免歧义，直方图会跟核密度估计函数一起使用
s.plot(kind='kde')

s.plot(kind='bar')

# 生成两个一维数组，符合正太分布，期望值分别为0和20
x1 = Series(np.random.normal(loc=0,scale=3,size=100))
x2 = Series(np.random.normal(loc=20,scale=5,size=100))
# 级联两个Series对象并重置索引
s = pd.concat((x1,x2),ignore_index=True)
s

s.plot(kind='hist',normed=True)
s.plot(kind='kde')

data = np.random.normal(size=(1000,4))
columns = list('ABCD')
df = DataFrame(data=data,columns=columns)
df.plot(x='A',y='B',kind='scatter')

pd.plotting.scatter_matrix(df,diagonal='kde')

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

data = pd.read_csv('data/type-.txt',sep='-',header=None)
data.columns = ['汇源','果汁','鸟']
data

table = pd.read_table('data/type_comma',sep=',',header=None)
table

table = pd.read_excel('data/students.xlsx',sheet_name=1)
table

table.to_excel('dancer.xlsx')

import sqlite3 as sqlite3

# SQL server  MongoDB  Redis

connection = sqlite3.connect('data/weather_2012.sqlite')

pd.read_sql('select * from weather_2012',connection)

table.to_sql('dancer',connection)

pd.read_sql('select * from dancer',connection)

# drop table dancer
connection.execute('drop table dancer')<sqlite3.Cursor at 0x130953e0>

pd.read_sql('select * from dancer',connection)

url = 'https://raw.githubusercontent.com/datasets/investor-flow-of-funds-us/master/data/weekly.csv'

pd.read_csv(url)

import numpy as np
import pandas as pd
from pandas import Series,DataFrame

# df = DataFrame({'sex':['man','man','women','women','man','women','man','women','women'],
#                'age':[15,23,25,17,35,57,24,31,22],
#                'smoke':[True,False,False,True,True,False,False,True,False],
#                'height':[168,179,181,166,173,178,188,190,160]})
df = pd.DataFrame({'foo': ['one','one','one','two','two','two'],
                       'bar': ['A', 'B', 'C', 'A', 'B', 'C'],
                       'baz': [1, 2, 3, 4, 5, 6]})

df

df.pivot_table(index='smoke',columns='sex',aggfunc=max)

df.pivot(index='bar',columns='foo',values='baz')

df.pivot(index='sex',columns=)

from pandas import pivot_table

df = DataFrame({'sex':['man','man','women','women','man','women','man','women','women'],
               'age':[15,23,25,17,35,57,24,31,22],
               'smoke':[True,False,False,True,True,False,False,True,False],
               'height':[168,179,181,166,173,178,188,190,160]})

pivot_table(df,values='age',index=['sex'],columns=['smoke'],aggfunc='min')

a = np.array(["foo", "foo", "foo", "foo", "bar", "bar","bar", "bar", "foo", "foo", "foo"], dtype=object)
b = np.array(["one", "one", "one", "two", "one", "one","one", "two", "two", "two", "one"], dtype=object)
c = np.array(["dull", "dull", "shiny", "dull", "dull", "shiny","shiny", "dull", "shiny", "shiny", "shiny"],dtype=object)
pd.crosstab(a, [b, c], rownames=['a'], colnames=['b', 'c'])

table = pd.read_csv('stock2015-2016.csv')

# 'AAPL', 'MSFT', 'GE', 'IBM', 'AA', 'DAL', 'UAL', 'PEP', 'KO'

table['Ticker'].unique()

按照每天查看苹果股票的收盘价格

adj_table = table.pivot(index='Date',columns='Ticker',values='Adj Close')

import matplotlib.pyplot as plt
%matplotlib inline
adj_table.plot()

adj_table['AAPL'].plot()

table.head()

adj_table.head()

table.groupby(['Ticker','Date'])['Adj Close'].mean().unstack(level=0).head()