Exploring Data Distribution | Set 1

Terms of Data Dissemination Research

 - & gt; Boxplot - & gt; Frequency Table - & gt; Histogram - & gt; Density Plot 
  • Boxplot: it is based on data percentiles as shown in the image below. The top and bottom of the boxplot represent the 75th th and 25th th percentiles of the data. The extended lines are known as whiskers, which include the range of the rest of the data. 

    To get link to csv file being used, click here .

    Code # 1: Loading Libraries

    import numpy as np

    import pandas as pd

    import seaborn as sns

    import matplotlib.pyplot as plt

    Code # 2: Loading data

    data = pd.read_csv ( " ../ data / state.csv " )

     
    # Add a new derived data column

    data [ `PopulationInMillions` ] = data [ `Population` ] / 1000000

     

    print (data.head ( 10 ))

    Output:

    Code # 3: BoxPlot

    # BoxPlot Population in millions

    fig, ax1 = plt.subplots ()

    fig.set_size_inches ( 9 15 )

     

    ax1 = sns.boxplot (x = data.PopulationInMillions, orient = "v" )

    ax1.set_ylabel ( " Population by Sta te in Millions " , fontsize = 15 )

    ax1.set_title ( "Population - BoxPlot" , fontsize = 20 )

    Output:

  • Frequency Table: is a tool for spreading data across evenly spaced ranges, segments and tells us how many values ​​are in each segment.

    Code # 1: Adding a column to execute crosstab and group functionality.

    # Perform binning action, binning has been made
    # selected to highlight the output for frequency table

     

    data [ `PopulationInMillionsBins` ] = pd.cut (

    data.PopulationInMillions, bins = [ 0 , 1 , 2 , 5 , 8 , 12 , 15 , 20 , 50 ])

     

    print (data.head ( 10 ))

    Output:

    Code # 2: crosstab — frequency table type

    # Cross Tab - frequency table type

     

    pd.crosstab (data.PopulationInMillionsBins, data.Abbreviation, margins = True )

    Output:

    Code # 3: GroupBy — frequency table type

    # Groupby - frequency table type

      

    data.groupby (data.PopulationInMillionsBins) [ `Abbreviation` ]. apply ( `, ` . join)

    Output: