In [2]:

    

!ls


    

    




BAMM.101x           Learn Jupyter.ipynb cookie.py           thinkbayes.py
Hash_Encryption     README.md           machine_learning    学术画像
LICENSE             __pycache__         structure&algorithm 线程进程

In [6]:

    

# %load cookie.py
"""This file contains code for use with "Think Bayes",
by Allen B. Downey, available from greenteapress.com

Copyright 2012 Allen B. Downey
License: GNU GPLv3 http://www.gnu.org/licenses/gpl.html
"""

from thinkbayes import Pmf

pmf = Pmf()
pmf.Set('Bowl 1', 0.5)
pmf.Set('Bowl 2', 0.5)

pmf.Mult('Bowl 1', 0.75)
pmf.Mult('Bowl 2', 0.5)

pmf.Normalize()

print((pmf.Prob('Bowl 1')))


    

    




0.6000000000000001

In [10]:

    

!pip install version_information


    

    




Collecting version_information
  Downloading version_information-1.0.3.tar.gz
Building wheels for collected packages: version-information
  Running setup.py bdist_wheel for version-information ... done
  Stored in directory: /Users/Beck/Library/Caches/pip/wheels/4b/4c/f7/4d99d7820a507d8ae55204fcc00d66cdabf596d4b01228e7bd
Successfully built version-information
Installing collected packages: version-information
Successfully installed version-information-1.0.3

In [12]:

    

%load_ext version_information
%version_information pandas, sklearn


    

    




The version_information extension is already loaded. To reload it, use:
  %reload_ext version_information






    
Out[12]:




Software
Version
Python
3.5.2 64bit [GCC 4.2.1 Compatible Apple LLVM 4.2 (clang-425.0.28)]
IPython
6.2.0
OS
Darwin 15.6.0 x86_64 i386 64bit
pandas
0.20.3
sklearn
0.19.0
Wed Sep 20 13:50:44 2017 CST

In [13]:

    

%whos


    

    




Variable   Type    Data/Info
----------------------------
Pmf        type    <class 'thinkbayes.Pmf'>
pmf        Pmf     <thinkbayes.Pmf object at 0x1073309b0>

In [14]:

    

# 自动刷新引用
%load_ext autoreload
%audoreload 2
%aimport cookie


    

    




UsageError: Line magic function `%audoreload` not found.

In [18]:

    

# 用于展示引用文件
from IPython.display import FileLink
FileLink("cookie.py")


    

    
Out[18]:




cookie.py

In [28]:

    

import numpy as np
import sklearn 
import pandas
%matplotlib inline
import matplotlib.pyplot as plt


    

In [22]:

    

from sklearn.datasets import load_boston


    

In [1]:

    

# 在括号内按 shitf + tab
load_boston()


    

    




---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
<ipython-input-1-2fcfa8cd1960> in <module>()
      1 # 在括号内按 shitf + tab
----> 2 load_boston()

NameError: name 'load_boston' is not defined

In [25]:

    

from sklearn.ensemble import RandomForestRegressor
RandomForestRegressor?


    

In [33]:

    

%%latex
$$ x^3 + C = \int{\frac{1}{3} x^2 \; dx} \quad (C \in \mathbb{R})$$


    

    






$$ x^3 + C = \int{\frac{1}{3} x^2 \; dx} \quad (C \in \mathbb{R})$$

In [2]:

    

import sklearn 
import numpy as np
import pandas as pd
%matplotlib inline
import matplotlib.pyplot as plt


    

In [3]:

    

from sklearn.datasets import california_housing
cal = california_housing.fetch_california_housing()
df = pd.DataFrame(data=cal.data, columns=cal.feature_names, index=cal.target)
df.head(10)


    

    




Downloading Cal. housing from https://ndownloader.figshare.com/files/5976036 to /Users/Beck/scikit_learn_data






    
Out[3]:







  

    

      

      
MedInc
      
HouseAge
      
AveRooms
      
AveBedrms
      
Population
      
AveOccup
      
Latitude
      
Longitude
    
  
  

    

      
4.526
      
8.3252
      
41.0
      
6.984127
      
1.023810
      
322.0
      
2.555556
      
37.88
      
-122.23
    
    

      
3.585
      
8.3014
      
21.0
      
6.238137
      
0.971880
      
2401.0
      
2.109842
      
37.86
      
-122.22
    
    

      
3.521
      
7.2574
      
52.0
      
8.288136
      
1.073446
      
496.0
      
2.802260
      
37.85
      
-122.24
    
    

      
3.413
      
5.6431
      
52.0
      
5.817352
      
1.073059
      
558.0
      
2.547945
      
37.85
      
-122.25
    
    

      
3.422
      
3.8462
      
52.0
      
6.281853
      
1.081081
      
565.0
      
2.181467
      
37.85
      
-122.25
    
    

      
2.697
      
4.0368
      
52.0
      
4.761658
      
1.103627
      
413.0
      
2.139896
      
37.85
      
-122.25
    
    

      
2.992
      
3.6591
      
52.0
      
4.931907
      
0.951362
      
1094.0
      
2.128405
      
37.84
      
-122.25
    
    

      
2.414
      
3.1200
      
52.0
      
4.797527
      
1.061824
      
1157.0
      
1.788253
      
37.84
      
-122.25
    
    

      
2.267
      
2.0804
      
42.0
      
4.294118
      
1.117647
      
1206.0
      
2.026891
      
37.84
      
-122.26
    
    

      
2.611
      
3.6912
      
52.0
      
4.970588
      
0.990196
      
1551.0
      
2.172269
      
37.84
      
-122.25
    
  

In [4]:

    

plt.scatter(df.Latitude, df.Longitude)


    

    
Out[4]:





<matplotlib.collections.PathCollection at 0x11005fc88>






    

In [5]:

    

import seaborn as sns


    

In [7]:

    

sns.jointplot(df.Longitude, df.Latitude)


    

    
Out[7]:





<seaborn.axisgrid.JointGrid at 0x1138c2b38>






    

In [9]:

    

sns.set(style="ticks")

sns.jointplot(df.Longitude, df.Latitude, kind="hex", color="#4CB391")


    

    
Out[9]:





<seaborn.axisgrid.JointGrid at 0x11b12ea20>






    

In [13]:

    

from scipy.stats import kendalltau
kendalltau?


    

In [14]:

    

sns.set(style="ticks")

sns.jointplot(df.Longitude, df.Latitude, kind="hex",stat_func=kendalltau, color="#4CB391")


    

    
Out[14]:





<seaborn.axisgrid.JointGrid at 0x11be1d9b0>






    

In [ ]: