In [2]:

    

import seaborn as sns
import pandas as pd
%matplotlib inline


    

In [4]:

    

cars=pd.read_csv("https://vincentarelbundock.github.io/Rdatasets/csv/datasets/mtcars.csv")


    

In [7]:

    

cars.columns


    

    
Out[7]:





Index(['Unnamed: 0', 'mpg', 'cyl', 'disp', 'hp', 'drat', 'wt', 'qsec', 'vs',
       'am', 'gear', 'carb'],
      dtype='object')

In [8]:

    

cars.columns=['Brand', 'mpg', 'cyl', 'disp', 'hp', 'drat', 'wt', 'qsec', 'vs','am', 'gear', 'carb']


    

In [9]:

    

cars.head()


    

    
Out[9]:






  

    

      

      
Brand
      
mpg
      
cyl
      
disp
      
hp
      
drat
      
wt
      
qsec
      
vs
      
am
      
gear
      
carb
    
  
  

    

      
0
      
Mazda RX4
      
21.0
      
6
      
160.0
      
110
      
3.90
      
2.620
      
16.46
      
0
      
1
      
4
      
4
    
    

      
1
      
Mazda RX4 Wag
      
21.0
      
6
      
160.0
      
110
      
3.90
      
2.875
      
17.02
      
0
      
1
      
4
      
4
    
    

      
2
      
Datsun 710
      
22.8
      
4
      
108.0
      
93
      
3.85
      
2.320
      
18.61
      
1
      
1
      
4
      
1
    
    

      
3
      
Hornet 4 Drive
      
21.4
      
6
      
258.0
      
110
      
3.08
      
3.215
      
19.44
      
1
      
0
      
3
      
1
    
    

      
4
      
Hornet Sportabout
      
18.7
      
8
      
360.0
      
175
      
3.15
      
3.440
      
17.02
      
0
      
0
      
3
      
2
    
  

In [10]:

    

sns.boxplot(x='gear',y='mpg',data=cars)


    

    
Out[10]:





<matplotlib.axes._subplots.AxesSubplot at 0xb5569e8>






    

In [11]:

    

sns.distplot(cars.mpg, bins=20, kde=True, rug=False)


    

    




C:\Users\Dell\Anaconda3\lib\site-packages\statsmodels\nonparametric\kdetools.py:20: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
  y = X[:m/2+1] + np.r_[0,X[m/2+1:],0]*1j






    
Out[11]:





<matplotlib.axes._subplots.AxesSubplot at 0x6696358>






    

In [12]:

    

sns.distplot(cars.hp, bins=20, kde=True, rug=False)


    

    




C:\Users\Dell\Anaconda3\lib\site-packages\statsmodels\nonparametric\kdetools.py:20: VisibleDeprecationWarning: using a non-integer number instead of an integer will result in an error in the future
  y = X[:m/2+1] + np.r_[0,X[m/2+1:],0]*1j






    
Out[12]:





<matplotlib.axes._subplots.AxesSubplot at 0x66961d0>






    

In [13]:

    

sns.jointplot('hp','mpg',data=cars)


    

    
Out[13]:





<seaborn.axisgrid.JointGrid at 0xbc37748>






    

In [14]:

    

sns.factorplot(x="gear", y="mpg",col="cyl", data=cars, kind="box", size=4, aspect=.5);


    

In [16]:

    

sns.factorplot(x="gear", y="mpg",col="cyl", data=cars, kind="bar", size=4, aspect=.5);


    

In [18]:

    

import os as os


    

In [19]:

    

os.getcwd()


    

    
Out[19]:





'C:\\Users\\Dell'

In [20]:

    

os.chdir('C:\\Users\\Dell\\Downloads\\')


    

In [21]:

    

os.listdir()


    

    
Out[21]:





['140749_2017.pdf',
 '2011-F01-0700-Rev4-MDDS.XLSX',
 '20150817143155.pdf',
 '20160111060911.pdf',
 '20170214052225.pdf',
 '7z1604-x64.exe',
 '7z1604.exe',
 '861415_10151432783238421_2124270505_o (1).jpg',
 '861415_10151432783238421_2124270505_o.jpg',
 'AirPassengers.csv',
 'ajayo.jpg',
 'Alison Python  Invoice   - Sheet1.pdf',
 'Alison SAS  Invoice   - Sheet1.pdf',
 'All+CSV+Files+in+a+Folder.ipynb',
 'Allison Interview Jones Invoice   - Sheet1.pdf',
 'Anaconda3-4.2.0-Windows-x86_64.exe',
 'anscombe+dataset.ipynb',
 'apachehttpd.exe',
 'April invoice adaptive analytics   - Sheet1.pdf',
 'Assignment14_BusinessAnalytics (1).docx',
 'Assignment14_BusinessAnalytics.docx',
 'Assignment15_BusinessAnalytics.docx',
 'Assignment16_BusinessAnalytics (1).docx',
 'Assignment16_BusinessAnalytics (2).docx',
 'Assignment16_BusinessAnalytics.docx',
 'aug ust 2008.JPG',
 'avast_free_antivirus_setup_online.exe',
 'avinash_ltv.zip',
 'BigDiamonds.csv',
 'BigDiamonds.csv (1).zip',
 'BigDiamonds.csv (2)',
 'BigDiamonds.csv (2).zip',
 'BigDiamonds.csv (3).zip',
 'BigDiamonds.csv.zip',
 'Boston (1).csv',
 'Boston.csv',
 'CAM- Ajay Ohri (1).pdf',
 'CAM- Ajay Ohri.pdf',
 'camtasia.exe',
 'ccFraud.csv',
 'Certificate of Incorporation - U74999DL2015PTC282030 (26 June 2015).pdf',
 'CHAP1-6PythonforRUsersAnapproachforDataScience.docx',
 'chapter+3+_+spark.html',
 'chi+square+test.ipynb',
 'chromeinstall-8u111.exe',
 'Cisco_WebEx_Add-On.exe',
 'class2.csv',
 'Collabera Invoice (1).pdf',
 'Collabera Invoice.pdf',
 'Collectcent Invoice.pdf',
 'college degrees.pdf',
 'DAP 1.pdf',
 'DAP 1.pptx',
 'DAP 6 RDBMS and SQL.pdf',
 'DAP 6 RDBMS and SQL.pptx',
 'Data Analysis (1).7z',
 'Data Analysis (1).rar',
 'Data Analysis (2).rar',
 'Data Analysis (3).rar',
 'Data Analysis.rar',
 'Data Viz.pptx',
 'data+exploration.ipynb',
 'data+manipulation.ipynb',
 'data+munging+again.ipynb',
 'data+viz.ipynb',
 'data+wrangling+titanic+dataset.ipynb',
 'data1.csv',
 'datasets.csv',
 'Decision Trees.pdf',
 'DecisionStatsOfferLetter.docx',
 'DecisionStatsRelievingLetter.docx',
 'descriptive+stats+in+Python.ipynb',
 'desktop.ini',
 'Diamond (1).csv',
 'Diamond (2).csv',
 'Diamond (3).csv',
 'Diamond (4).csv',
 'Diamond (5).csv',
 'Diamond (6).csv',
 'Diamond (7).csv',
 'Diamond (8).csv',
 'Diamond.csv',
 'DolbyVoiceClient.msi',
 'DropboxInstaller.exe',
 'edb_npgsql.exe',
 'edb_pgjdbc.exe',
 'edb_psqlodbc.exe',
 'edb_psqlodbc.exe-20170203172812',
 'edb_psqlodbc.exe-20170307203617',
 'final invoice edureka  - Sheet1.pdf',
 'FinalPythonforRUsersAnapproachforDataScience (1).docx',
 'FinalPythonforRUsersAnapproachforDataScience (2).docx',
 'FinalPythonforRUsersAnapproachforDataScience (3).docx',
 'FinalPythonforRUsersAnapproachforDataScience (4).docx',
 'FinalPythonforRUsersAnapproachforDataScience.docx',
 'final_webinar (1).pdf',
 'final_webinar.pdf',
 'Git-2.11.0-64-bit.exe',
 'Git-2.12.0-64-bit.exe',
 'GitHubSetup (1).exe',
 'GitHubSetup (2).exe',
 'GitHubSetup.exe',
 'GOMAUDIOGLOBALSETUP.EXE',
 'Hdma.csv',
 'Hedonic.csv',
 'HP Downloads',
 'HPSupportSolutionsFramework-12.5.32.203.exe',
 'image.png',
 'IMS PROSCHOOL Workshop.pptx.pdf',
 'IMS PROSCHOOL Workshop.pptx.pptx',
 'internship.docx',
 'Introduction to SAS (1).pdf',
 'Introduction to SAS Part 1 (1).pdf',
 'Introduction to SAS Part 1.pdf',
 'Introduction to SAS.pdf',
 'introductory+python.ipynb',
 'Invoice for Digital Vidya.pdf',
 'Invoice for Weekendr.pdf',
 'Invoice format - Ajay Ohri CONTATA (1).xls',
 'Invoice format - Ajay Ohri CONTATA.xls',
 'invoice rapid miner.pdf',
 'Invoice trafla format.docx',
 'iris2 (1).ipynb',
 'iris2 (2).ipynb',
 'iris2.ipynb',
 'January invoice Indicus  .pdf',
 'June AV   Invoice   - Sheet1.pdf',
 'Lecture 6 - KNN & Naive Bayes.ppt',
 'Local Disk (C) - Shortcut.lnk',
 'logistic regression - script for ppt.R',
 'logistic_regression_-_script_for_ppt.html',
 'lyncentry.exe',
 'March invoice Indicus   - Sheet1.pdf',
 'matplotlib+cars.ipynb',
 'matplotlib+line+graph.ipynb',
 'mongodb-win32-x86_64-2008plus-ssl-3.4.2-signed.msi',
 'mongodb-win32-x86_64-3.4.2-signed.msi',
 'mortDefault',
 'mortDefault.zip',
 'mtcarslm.R',
 'multiple+file+concat+in+pandas (1).ipynb',
 'multiple+file+concat+in+pandas.ipynb',
 'my+first+class+in+python.ipynb',
 'nltk.ipynb',
 'notebook-Copy1.html',
 'Offer Letter - Ajay Ohri (1).pdf',
 'Offer Letter - Ajay Ohri.pdf',
 'Other Data Mining  Methods (1).pdf',
 'Other Data Mining  Methods.pdf',
 'output1 (1).xls',
 'output1 (2).xls',
 'output1.xls',
 'pandas+11.ipynb',
 'pandas+analysis+1.ipynb',
 'pandas+data+manipulation.ipynb',
 'passport image.pdf',
 'Pawconinvoice2016.pdf',
 'Pawconinvoice2017 (1).pdf',
 'Pawconinvoice2017 (2).pdf',
 'Pawconinvoice2017 (3).pdf',
 'Pawconinvoice2017.pdf',
 'Payslip Feb 2016 - Sheet1.pdf',
 'Payslip Feb 2016.pdf',
 'Payslip Format Decisionstats - Sheet1.pdf',
 'Payslip Jan 2016 - Sheet1.pdf',
 'Payslip Jan 2016.pdf',
 'Payslip March 2016 - Sheet1.pdf',
 'Payslip March 2016.pdf',
 'pgd.csv',
 'postgresql-9.6.1-1-windows-x64.exe',
 'Program 1-results.rtf',
 'protein.csv',
 'python+with+postgres (1).ipynb',
 'python+with+postgres.ipynb',
 'Python.docx',
 'R-3.3.2-win.exe',
 'R-3.3.3-win.exe',
 'RCertificationExam.pdf',
 'reg+model.ipynb',
 'Revision -  Business Analytics (1).pdf',
 'Revision -  Business Analytics.pdf',
 'RidingMowers.csv',
 'rsconnect',
 'RStudio-1.0.136.exe',
 'Salary Slip, Feb 2016.pdf',
 'Salary Slip, Jan 2016.pdf',
 'Salary Slip, March 2016 (1).pdf',
 'Salary Slip, March 2016 (2).pdf',
 'Salary Slip, March 2016.pdf',
 'sales-of-shampoo-over-a-three-ye.csv',
 'SAS part 2.pdf',
 'SAS Part 3.pdf',
 'sas-university-edition-107140.pdf',
 'Scan0095.pdf',
 'Scanned Invoice for Collabera.pdf',
 'Screenshot 2017-01-23 12.36.55.png',
 'September invoice adaptive analytics   - Sheet1.pdf',
 'simple+matplot+graph.ipynb',
 'Sollers January.pdf',
 'sqlalchemy.ipynb',
 'stackoverflow-dump-analysis.html',
 'Sunstone.pdf',
 'Tableau.pdf',
 'TableauPublicDesktop-64bit-10-1-3.exe',
 'TableauPublicDesktop-64bit-10-1-4.exe',
 'telecom.csv',
 'TelecomServiceProviderCaseStudy.pdf',
 'test+web+scraping.ipynb',
 'Text Mining (1).pdf',
 'Text Mining.pdf',
 'third.sas7bdat',
 'Time Series  Forecasting (1).pdf',
 'Time Series  Forecasting.pdf',
 'ts.html',
 'ts.R',
 'Unconfirmed 373974.crdownload',
 'Unconfirmed 376991.crdownload',
 'Unconfirmed 950045.crdownload',
 'uTorrent.exe',
 'VirtualBox-5.1.8-111374-Win (1).exe',
 'VirtualBox-5.1.8-111374-Win.exe',
 'visualcppbuildtools_full.exe',
 'Web+Scraping+Yelp+with+Beautiful+Soup.ipynb',
 'Webinar for Business Analytics.pdf',
 'WhatsApp Image 2017-02-18 at 08.42.55 (1).jpeg',
 'WhatsApp Image 2017-02-18 at 08.42.55.jpeg']

In [22]:

    

fraud=pd.read_csv("ccFraud.csv")


    

In [25]:

    

fraud.columns


    

    
Out[25]:





Index(['custID', 'gender', 'state', 'cardholder', 'balance', 'numTrans',
       'numIntlTrans', 'creditLine', 'fraudRisk'],
      dtype='object')

In [26]:

    

sns.boxplot(x='fraudRisk',y='balance',data=fraud)


    

    
Out[26]:





<matplotlib.axes._subplots.AxesSubplot at 0xc2592b0>






    

In [ ]:

    

sns.factorplot(x="gender", y="balance",col="fraudRisk", data=fraud, kind="bar", size=4, aspect=.5);


    

In [ ]:

    

sns.distplot(fraud.fraudRisk, bins=20, kde=True, rug=False)