path: root/cbse/pandas.ipyml

cells:

- markdown: |
    Pandas
    ======
    
    - Provides a powerful `DataFrame` object.
    - Makes it easy to deal with "Tabular" data.
    - Very easy to read, process and visualize data.
    - See http://pandas.pydata.org


- code: |
    %matplotlib inline
    import numpy as np
    import pandas as pd

  id: 0

- code: |
    x = np.linspace(0, 2*np.pi, 100)
    sin = np.sin(x)
    cos = np.cos(x)

  id: 1

- code: |
    df = pd.DataFrame({'x': x, 'sin': sin, 'cos': cos, 'x-data':x})
    # OR
    #df = pd.DataFrame(dict(x=x, sin=sin, cos=cos))

  id: 2

- code: |
    df.head() # or df.tail()

  id: 3

- code: |
    df.tail()

  id: 4

- code: |
    df.describe()

  id: 5

- code: |
    df1 = df[10:13]
    df1.head()

  id: 6

- code: |
    df.x[::10]

  id: 7

- code: |
    df1.describe()

  id: 8

- code: |
    # df.x-data[:5] will not work!!
    df['x-data'][:5]

  id: 9

- code: |
    df['x'][:5]

  id: 10

- code: |
    df.x[:10]

  id: 11

- code: |
    df.columns

  id: 12

- code: |
    len(df)

  id: 13

- code: |
    df.index

  id: 14

- code: |
    df1 = df.copy()
    df1.head()

  id: 15

- markdown: |
    Indexing
    =========
    
    - Give me a data frame, where all cosine values are >0.


- code: |
    y = np.linspace(10, 11, 11)
    y

  id: 16

- code: |
    y> 10.5

  id: 17

- code: |
    cond = y > 10.5
    y[y > 10.7]

  id: 18

- code: |


  id: 19

- code: |


  id: 20

- code: |


  id: 21

- code: |
    condition = df.cos > 0.0
    print(len(condition))

  id: 22

- code: |
    df_positive_cos = df[condition]
    df_positive_cos.describe()

  id: 23

- code: |
    # Combining conditionals
    cond1 = df.sin > 0.0
    df_all_positive = df[condition & cond1]
    df_all_positive.describe()

  id: 24

- code: |
    df_all_positive = df[(df.cos > 0.0) & (df.sin > 0)]
    df_all_positive.describe()

  id: 25

- code: |
    c = np.array([True, False, True, False])
    c1 = np.array([False, True, False, False])
    ~(c | c1)

  id: 26

- code: |
    cond1 = df_positive_cos.sin > 0.0
    df_all_positive = df_positive_cos[cond1]
    df_all_positive.describe()

  id: 27

- code: |


  id: 28

- code: |
    # This adds a new column sincos
    df['sincos'] = df.sin*df.cos
    len(df.sincos)

  id: 29

- code: |
    df.describe()

  id: 30

- code: |
    # Remove a column with del.
    if 'x-data' in df:
        del df['x-data']
    df.head()

  id: 31

- markdown: |
    Plotting
    =========


- code: |
    df.plot() 
    # or
    #df.plot.line()

  id: 32

- markdown: |
    Notice that everything is plotted w.r.t. the index!
    Let us fix this!


- code: |
    df.plot.line(x='x', y=['sin', 'cos'])

  id: 33

- code: |
    # See what this does
    
    df[(df.sin > 0.0) ^ (df.cos < 0.0)].plot.line(x='x', marker='o')

  id: 34

- code: |
    df.plot.hist(y='cos')
    # or
    #df.plot(y='cos', kind='hist')

  id: 35

- markdown: |
    Input and output CSV and other file formats
    --------------------------------------------
    
    - `pd.read_csv()`
    - `df.to_csv()`
    - Can read/save to clip board.
    - Directly read from URLs.


- code: |
    df.to_csv('sincos.csv', index=False)

  id: 36

- code: |
    df1 = pd.read_csv('sincos.csv')
    df1.head()

  id: 37

- code: |


  id: 38

- code: |


  id: 39

- markdown: |
    ### Conversion to LaTeX and HTML


- code: |
    print(df[:5].to_latex())

  id: 40

- code: |
    print(df[:5].to_latex(index=False))

  id: 41

- code: |
    print(df[:5].to_html())

  id: 42

- code: |
    from IPython.display import HTML
    HTML(df[:5].to_html())

  id: 43

- markdown: |
    Selecting from the clipboard
    =============================
    
    - Let us select data from wikipedia:
    - https://en.wikipedia.org/wiki/List_of_countries_by_GDP_(nominal)_per_capita
    
    Select some data and then do this:


- code: |
    df2 = pd.read_clipboard()
    df2.columns = ['index', 'country', 'GDP']
    df2.head()

  id: 44

- code: |
    url = 'http://www.aero.iitb.ac.in/~prabhu/tmp/sslc_small.csv'
    df = pd.read_csv(url, sep=';')

  id: 45

- code: |
    df.head()
    #df.describe()

  id: 46

- code: |
    df.fl.iloc[0] = np.nan

  id: 47

- code: |
    df.head()

  id: 48

- code: |
    df.describe()

  id: 49

- code: |
    pd.read_csv?

  id: 50

- markdown: |
    Exercise
    --------
    
    Look at the following:
    
    - https://data.gov.in/catalog/annual-and-seasonal-maximum-temperature-india
    - https://data.gov.in/catalog/annual-and-seasonal-minimum-temperature-india
    
    
    Download the csv file into a `datafile.csv` on your machine.


- code: |
    df = pd.read_csv('datafile.csv')
    df.head()

  id: 51

- code: |
    df.plot.line(x='YEAR')

  id: 52

- code: |


  id: 53

- markdown: |
    Exercise
    ---------
    
    
    Consider a smaller file:
    
    - File is at: http://www.aero.iitb.ac.in/~prabhu/tmp/sslc_small.csv


- code: |
    url = 'http://www.aero.iitb.ac.in/~prabhu/tmp/sslc_small.csv'
    df = pd.read_csv(url)
    df.head()  # Produces only one strange column of data!

  id: 54

- markdown: |
    Notice that this data is read incorrectly, this is because the separator is not a comma but a ';' so use this.


- code: |
    df = pd.read_csv(url, sep=';')
    df.head()

  id: 55

- code: |
    df['region'].value_counts()

  id: 56

- code: |
    df.plot.scatter(x='fl', y='math')

  id: 57

- markdown: |
    There are more options to `pd.read_csv`, for example if `'AA'` is a value indicating a non-existing value you can pass an option, called `na_values`.  Read more on the documentation for `read_csv`.


- code: |
    url = 'http://www.aero.iitb.ac.in/~prabhu/tmp/sslc1.csv.gz'

  id: 58

- markdown: |
    - This has a very large CSV file that is gzipped to save space. 
    - It can be loaded with the same method.
    - You can download it and see the file.
    
    To unzip it if you want you can do
    
    ```
    $ gunzip sslc1.csv.gz
    ```
    
    The file has missing values in the form of 'AA' entries for absent students.


- code: |
    df = pd.read_csv(url, sep=';', na_values='AA')

  id: 59

- markdown: |
    If you have the `sslc1.csv` file locally you can do this:


- code: |
    df = pd.read_csv('sslc1.csv', sep=';', na_values='AA')
    df.head()

  id: 60

- code: |
    df.describe()

  id: 61

- code: |
    df['pass'].value_counts()

  id: 62

- code: |
    df.groupby('region')['pass'].value_counts()

  id: 63

- code: |
    df.plot.hist(y='sl')

  id: 64

- markdown: |
    ## Pivoting
    
    - Powerful operation to group the data
    - Performs a multi-dimensional summarization of the data
    
    Here is a simple example


- code: |
    pd.pivot_table(df, index=['region'])

  id: 65

- markdown: |
    The default aggregation function here is an average, i.e. `np.average`.


- code: |
    # This is not useful but tells you how this can be changed.
    pd.pivot_table(df, index=['region'], aggfunc=np.sum)

  id: 66

- markdown: |
    More information
    ==================
    
    - http://pandas.pydata.org
    - Go through the tutorials here:
    
    http://nbviewer.jupyter.org/github/jvns/pandas-cookbook/tree/v0.1/cookbook/
    
    - Go over chapter 1 to 7.
    
    Excellent material on pivot tables with pandas 
    
    - https://pbpython.com/pandas-pivot-table-explained.html
    
    An excellent book on data science related tools has a nice section on pivot tables.
    
    - https://jakevdp.github.io/PythonDataScienceHandbook/03.09-pivot-tables.html
    
    Also has other material on pandas
    
    - https://jakevdp.github.io/PythonDataScienceHandbook/03.00-introduction-to-pandas.html
    
    The notebooks can also be edited live if you wish.


- code: |


  id: 67

# The lines below here may be deleted if you do not need them.
# ---------------------------------------------------------------------------
metadata:
  kernelspec:
    display_name: Python 3
    language: python
    name: python3
  language_info:
    codemirror_mode:
      name: ipython
      version: 3
    file_extension: .py
    mimetype: text/x-python
    name: python
    nbconvert_exporter: python
    pygments_lexer: ipython3
    version: 3.6.0
nbformat: 4
nbformat_minor: 1

# ---------------------------------------------------------------------------
data:
  [{execution_count: 1, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: null, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: 56, outputs: []}, {execution_count: 62, outputs: [{data: {text/html: "<div>\n\
              <style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align:\
              \ middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align:\
              \ top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n\
              \    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n\
              \    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>region</th>\n\
              \      <th>roll_number</th>\n      <th>name</th>\n      <th>fl</th>\n\
              \      <th>sl</th>\n      <th>math</th>\n      <th>sci</th>\n      <th>ss</th>\n\
              \      <th>total</th>\n      <th>pass</th>\n      <th>withheld</th>\n\
              \      <th>extra</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n  \
              \    <th>0</th>\n      <td>A</td>\n      <td>10001</td>\n      <td>T N</td>\n\
              \      <td>53</td>\n      <td>36</td>\n      <td>28</td>\n      <td>16</td>\n\
              \      <td>44</td>\n      <td>177</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>A</td>\n\
              \      <td>10002</td>\n      <td>A R</td>\n      <td>58</td>\n      <td>37</td>\n\
              \      <td>42</td>\n      <td>35</td>\n      <td>40</td>\n      <td>212</td>\n\
              \      <td>P</td>\n      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n\
              \    <tr>\n      <th>2</th>\n      <td>A</td>\n      <td>10003</td>\n\
              \      <td>A M</td>\n      <td>72</td>\n      <td>56</td>\n      <td>71</td>\n\
              \      <td>55</td>\n      <td>70</td>\n      <td>324</td>\n      <td>P</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n\
              \      <td>A</td>\n      <td>10004</td>\n      <td>S A</td>\n      <td>87</td>\n\
              \      <td>64</td>\n      <td>83</td>\n      <td>58</td>\n      <td>65</td>\n\
              \      <td>357</td>\n      <td>P</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \    </tr>\n    <tr>\n      <th>4</th>\n      <td>A</td>\n      <td>10005</td>\n\
              \      <td>N A</td>\n      <td>59</td>\n      <td>45</td>\n      <td>50</td>\n\
              \      <td>35</td>\n      <td>48</td>\n      <td>237</td>\n      <td>P</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n\
              </div>", text/plain: '  region  roll_number name  fl  sl  math  sci  ss  total
              pass  withheld  extra
  
              0      A        10001  T N  53  36    28   16  44    177  NaN       NaN    NaN
  
              1      A        10002  A R  58  37    42   35  40    212    P       NaN    NaN
  
              2      A        10003  A M  72  56    71   55  70    324    P       NaN    NaN
  
              3      A        10004  S A  87  64    83   58  65    357    P       NaN    NaN
  
              4      A        10005  N A  59  45    50   35  48    237    P       NaN    NaN'},
          execution_count: 62, metadata: {}, output_type: execute_result}]}, {execution_count: 66,
      outputs: []}, {execution_count: 68, outputs: [{data: {text/html: "<div>\n<style\
              \ scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align:\
              \ middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align:\
              \ top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n\
              \    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n\
              \    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>region</th>\n\
              \      <th>roll_number</th>\n      <th>name</th>\n      <th>fl</th>\n\
              \      <th>sl</th>\n      <th>math</th>\n      <th>sci</th>\n      <th>ss</th>\n\
              \      <th>total</th>\n      <th>pass</th>\n      <th>withheld</th>\n\
              \      <th>extra</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n  \
              \    <th>0</th>\n      <td>A</td>\n      <td>10001</td>\n      <td>T N</td>\n\
              \      <td>NaN</td>\n      <td>36</td>\n      <td>28</td>\n      <td>16</td>\n\
              \      <td>44</td>\n      <td>177</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n      <td>A</td>\n\
              \      <td>10002</td>\n      <td>A R</td>\n      <td>58.0</td>\n     \
              \ <td>37</td>\n      <td>42</td>\n      <td>35</td>\n      <td>40</td>\n\
              \      <td>212</td>\n      <td>P</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \    </tr>\n    <tr>\n      <th>2</th>\n      <td>A</td>\n      <td>10003</td>\n\
              \      <td>A M</td>\n      <td>72.0</td>\n      <td>56</td>\n      <td>71</td>\n\
              \      <td>55</td>\n      <td>70</td>\n      <td>324</td>\n      <td>P</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n\
              \      <td>A</td>\n      <td>10004</td>\n      <td>S A</td>\n      <td>87.0</td>\n\
              \      <td>64</td>\n      <td>83</td>\n      <td>58</td>\n      <td>65</td>\n\
              \      <td>357</td>\n      <td>P</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \    </tr>\n    <tr>\n      <th>4</th>\n      <td>A</td>\n      <td>10005</td>\n\
              \      <td>N A</td>\n      <td>59.0</td>\n      <td>45</td>\n      <td>50</td>\n\
              \      <td>35</td>\n      <td>48</td>\n      <td>237</td>\n      <td>P</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n\
              </div>", text/plain: "  region  roll_number name    fl  sl  math  sci\
              \  ss  total pass  withheld  \\\n0      A        10001  T N   NaN  36\
              \    28   16  44    177  NaN       NaN   \n1      A        10002  A R\
              \  58.0  37    42   35  40    212    P       NaN   \n2      A        10003\
              \  A M  72.0  56    71   55  70    324    P       NaN   \n3      A   \
              \     10004  S A  87.0  64    83   58  65    357    P       NaN   \n4\
              \      A        10005  N A  59.0  45    50   35  48    237    P      \
              \ NaN   \n\n   extra  \n0    NaN  \n1    NaN  \n2    NaN  \n3    NaN \
              \ \n4    NaN  "}, execution_count: 68, metadata: {}, output_type: execute_result}]},
    {execution_count: 67, outputs: [{data: {text/html: "<div>\n<style scoped>\n    .dataframe\
              \ tbody tr th:only-of-type {\n        vertical-align: middle;\n    }\n\
              \n    .dataframe tbody tr th {\n        vertical-align: top;\n    }\n\n\
              \    .dataframe thead th {\n        text-align: right;\n    }\n</style>\n\
              <table border=\"1\" class=\"dataframe\">\n  <thead>\n    <tr style=\"\
              text-align: right;\">\n      <th></th>\n      <th>roll_number</th>\n \
              \     <th>fl</th>\n      <th>sl</th>\n      <th>math</th>\n      <th>sci</th>\n\
              \      <th>ss</th>\n      <th>total</th>\n      <th>withheld</th>\n  \
              \    <th>extra</th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n    \
              \  <th>count</th>\n      <td>40.000000</td>\n      <td>39.000000</td>\n\
              \      <td>40.000000</td>\n      <td>40.000000</td>\n      <td>40.000000</td>\n\
              \      <td>40.000000</td>\n      <td>40.000000</td>\n      <td>0.0</td>\n\
              \      <td>0.0</td>\n    </tr>\n    <tr>\n      <th>mean</th>\n      <td>27708.800000</td>\n\
              \      <td>73.230769</td>\n      <td>56.375000</td>\n      <td>65.425000</td>\n\
              \      <td>51.825000</td>\n      <td>63.500000</td>\n      <td>309.850000</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>std</th>\n\
              \      <td>29338.523097</td>\n      <td>12.616742</td>\n      <td>15.903052</td>\n\
              \      <td>23.915329</td>\n      <td>18.092196</td>\n      <td>17.558693</td>\n\
              \      <td>81.745869</td>\n      <td>NaN</td>\n      <td>NaN</td>\n  \
              \  </tr>\n    <tr>\n      <th>min</th>\n      <td>10001.000000</td>\n\
              \      <td>43.000000</td>\n      <td>36.000000</td>\n      <td>25.000000</td>\n\
              \      <td>16.000000</td>\n      <td>35.000000</td>\n      <td>161.000000</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>25%</th>\n\
              \      <td>19495.750000</td>\n      <td>65.500000</td>\n      <td>44.000000</td>\n\
              \      <td>44.750000</td>\n      <td>36.750000</td>\n      <td>50.000000</td>\n\
              \      <td>247.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n \
              \   </tr>\n    <tr>\n      <th>50%</th>\n      <td>27395.500000</td>\n\
              \      <td>75.000000</td>\n      <td>53.500000</td>\n      <td>61.500000</td>\n\
              \      <td>52.000000</td>\n      <td>61.500000</td>\n      <td>304.000000</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>75%</th>\n\
              \      <td>29276.250000</td>\n      <td>83.000000</td>\n      <td>70.250000</td>\n\
              \      <td>86.750000</td>\n      <td>60.250000</td>\n      <td>74.500000</td>\n\
              \      <td>357.000000</td>\n      <td>NaN</td>\n      <td>NaN</td>\n \
              \   </tr>\n    <tr>\n      <th>max</th>\n      <td>199976.000000</td>\n\
              \      <td>90.000000</td>\n      <td>90.000000</td>\n      <td>100.000000</td>\n\
              \      <td>86.000000</td>\n      <td>97.000000</td>\n      <td>456.000000</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n\
              </div>", text/plain: "         roll_number         fl         sl     \
              \   math        sci         ss  \\\ncount      40.000000  39.000000  40.000000\
              \   40.000000  40.000000  40.000000   \nmean    27708.800000  73.230769\
              \  56.375000   65.425000  51.825000  63.500000   \nstd     29338.523097\
              \  12.616742  15.903052   23.915329  18.092196  17.558693   \nmin    \
              \ 10001.000000  43.000000  36.000000   25.000000  16.000000  35.000000\
              \   \n25%     19495.750000  65.500000  44.000000   44.750000  36.750000\
              \  50.000000   \n50%     27395.500000  75.000000  53.500000   61.500000\
              \  52.000000  61.500000   \n75%     29276.250000  83.000000  70.250000\
              \   86.750000  60.250000  74.500000   \nmax    199976.000000  90.000000\
              \  90.000000  100.000000  86.000000  97.000000   \n\n            total\
              \  withheld  extra  \ncount   40.000000       0.0    0.0  \nmean   309.850000\
              \       NaN    NaN  \nstd     81.745869       NaN    NaN  \nmin    161.000000\
              \       NaN    NaN  \n25%    247.000000       NaN    NaN  \n50%    304.000000\
              \       NaN    NaN  \n75%    357.000000       NaN    NaN  \nmax    456.000000\
              \       NaN    NaN  "}, execution_count: 67, metadata: {}, output_type: execute_result}]},
    {execution_count: 69, outputs: []}, {execution_count: null, outputs: []}, {execution_count: null,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: 70, outputs: [
        {data: {text/html: "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type\
              \ {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr\
              \ th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th\
              \ {\n        text-align: right;\n    }\n</style>\n<table border=\"1\"\
              \ class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\"\
              >\n      <th></th>\n      <th>region;roll_number;name;fl;sl;math;sci;ss;total;pass;withheld;extra</th>\n\
              \    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>0</th>\n      <td>A;010001;T\
              \ N;053;036;28;16;44;177;;;</td>\n    </tr>\n    <tr>\n      <th>1</th>\n\
              \      <td>A;010002;A R;058;037;42;35;40;212;P;;</td>\n    </tr>\n   \
              \ <tr>\n      <th>2</th>\n      <td>A;010003;A M;072;056;71;55;70;324;P;;</td>\n\
              \    </tr>\n    <tr>\n      <th>3</th>\n      <td>A;010004;S A;087;064;83;58;65;357;P;;</td>\n\
              \    </tr>\n    <tr>\n      <th>4</th>\n      <td>A;010005;N A;059;045;50;35;48;237;P;;</td>\n\
              \    </tr>\n  </tbody>\n</table>\n</div>", text/plain: "  region;roll_number;name;fl;sl;math;sci;ss;total;pass;withheld;extra\n\
              0               A;010001;T N;053;036;28;16;44;177;;;                 \n\
              1              A;010002;A R;058;037;42;35;40;212;P;;                 \n\
              2              A;010003;A M;072;056;71;55;70;324;P;;                 \n\
              3              A;010004;S A;087;064;83;58;65;357;P;;                 \n\
              4              A;010005;N A;059;045;50;35;48;237;P;;                 "},
          execution_count: 70, metadata: {}, output_type: execute_result}]}, {execution_count: 71,
      outputs: [{data: {text/html: "<div>\n<style scoped>\n    .dataframe tbody tr th:only-of-type\
              \ {\n        vertical-align: middle;\n    }\n\n    .dataframe tbody tr\
              \ th {\n        vertical-align: top;\n    }\n\n    .dataframe thead th\
              \ {\n        text-align: right;\n    }\n</style>\n<table border=\"1\"\
              \ class=\"dataframe\">\n  <thead>\n    <tr style=\"text-align: right;\"\
              >\n      <th></th>\n      <th>region</th>\n      <th>roll_number</th>\n\
              \      <th>name</th>\n      <th>fl</th>\n      <th>sl</th>\n      <th>math</th>\n\
              \      <th>sci</th>\n      <th>ss</th>\n      <th>total</th>\n      <th>pass</th>\n\
              \      <th>withheld</th>\n      <th>extra</th>\n    </tr>\n  </thead>\n\
              \  <tbody>\n    <tr>\n      <th>0</th>\n      <td>A</td>\n      <td>10001</td>\n\
              \      <td>T N</td>\n      <td>53</td>\n      <td>36</td>\n      <td>28</td>\n\
              \      <td>16</td>\n      <td>44</td>\n      <td>177</td>\n      <td>NaN</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>1</th>\n\
              \      <td>A</td>\n      <td>10002</td>\n      <td>A R</td>\n      <td>58</td>\n\
              \      <td>37</td>\n      <td>42</td>\n      <td>35</td>\n      <td>40</td>\n\
              \      <td>212</td>\n      <td>P</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \    </tr>\n    <tr>\n      <th>2</th>\n      <td>A</td>\n      <td>10003</td>\n\
              \      <td>A M</td>\n      <td>72</td>\n      <td>56</td>\n      <td>71</td>\n\
              \      <td>55</td>\n      <td>70</td>\n      <td>324</td>\n      <td>P</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n    <tr>\n      <th>3</th>\n\
              \      <td>A</td>\n      <td>10004</td>\n      <td>S A</td>\n      <td>87</td>\n\
              \      <td>64</td>\n      <td>83</td>\n      <td>58</td>\n      <td>65</td>\n\
              \      <td>357</td>\n      <td>P</td>\n      <td>NaN</td>\n      <td>NaN</td>\n\
              \    </tr>\n    <tr>\n      <th>4</th>\n      <td>A</td>\n      <td>10005</td>\n\
              \      <td>N A</td>\n      <td>59</td>\n      <td>45</td>\n      <td>50</td>\n\
              \      <td>35</td>\n      <td>48</td>\n      <td>237</td>\n      <td>P</td>\n\
              \      <td>NaN</td>\n      <td>NaN</td>\n    </tr>\n  </tbody>\n</table>\n\
              </div>", text/plain: '  region  roll_number name  fl  sl  math  sci  ss  total
              pass  withheld  extra
  
              0      A        10001  T N  53  36    28   16  44    177  NaN       NaN    NaN
  
              1      A        10002  A R  58  37    42   35  40    212    P       NaN    NaN
  
              2      A        10003  A M  72  56    71   55  70    324    P       NaN    NaN
  
              3      A        10004  S A  87  64    83   58  65    357    P       NaN    NaN
  
              4      A        10005  N A  59  45    50   35  48    237    P       NaN    NaN'},
          execution_count: 71, metadata: {}, output_type: execute_result}]}, {execution_count: 72,
      outputs: [{data: {text/plain: 'C    13
  
              B     9
  
              A     9
  
              D     9
  
              Name: region, dtype: int64'}, execution_count: 72, metadata: {}, output_type: execute_result}]},
    {execution_count: 73, outputs: [{data: {text/plain: <matplotlib.axes._subplots.AxesSubplot
              at 0x11ee08828>}, execution_count: 73, metadata: {}, output_type: execute_result},
        {data: {image/png: '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
  
              ', text/plain: <Figure size 432x288 with 1 Axes>}, metadata: {needs_background: light},
          output_type: display_data}]}, {execution_count: 3, outputs: []}, {execution_count: 4,
      outputs: []}, {execution_count: null, outputs: []}, {execution_count: null, outputs: []},
    {execution_count: 14, outputs: [{data: {text/plain: 'P    159072
  
              Name: pass, dtype: int64'}, execution_count: 14, metadata: {}, output_type: execute_result}]},
    {execution_count: 18, outputs: [{data: {text/plain: 'region  pass
  
              A       P       31013
  
              B       P       36202
  
              C       P       26681
  
              D       P       22080
  
              E       P       20880
  
              F       P       22216
  
              Name: pass, dtype: int64'}, execution_count: 18, metadata: {}, output_type: execute_result}]},
    {execution_count: null, outputs: []}, {execution_count: 7, outputs: [{data: {text/html: "<div>\n\
              <style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align:\
              \ middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align:\
              \ top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n\
              \    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n\
              \    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>fl</th>\n\
              \      <th>math</th>\n      <th>roll_number</th>\n      <th>sci</th>\n\
              \      <th>sl</th>\n      <th>ss</th>\n      <th>total</th>\n    </tr>\n\
              \    <tr>\n      <th>region</th>\n      <th></th>\n      <th></th>\n \
              \     <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n \
              \     <th></th>\n    </tr>\n  </thead>\n  <tbody>\n    <tr>\n      <th>A</th>\n\
              \      <td>54.156497</td>\n      <td>63.149551</td>\n      <td>105609.081674</td>\n\
              \      <td>50.432756</td>\n      <td>73.686377</td>\n      <td>62.453164</td>\n\
              \      <td>303.789099</td>\n    </tr>\n    <tr>\n      <th>B</th>\n  \
              \    <td>55.239836</td>\n      <td>63.638822</td>\n      <td>105746.142280</td>\n\
              \      <td>52.747653</td>\n      <td>74.455093</td>\n      <td>64.448891</td>\n\
              \      <td>310.482572</td>\n    </tr>\n    <tr>\n      <th>C</th>\n  \
              \    <td>54.080346</td>\n      <td>62.733572</td>\n      <td>124099.117879</td>\n\
              \      <td>50.344222</td>\n      <td>74.076716</td>\n      <td>64.647672</td>\n\
              \      <td>305.822393</td>\n    </tr>\n    <tr>\n      <th>D</th>\n  \
              \    <td>52.968296</td>\n      <td>62.589993</td>\n      <td>86303.811307</td>\n\
              \      <td>51.186670</td>\n      <td>73.665423</td>\n      <td>64.119590</td>\n\
              \      <td>304.428818</td>\n    </tr>\n    <tr>\n      <th>E</th>\n  \
              \    <td>52.085389</td>\n      <td>62.724153</td>\n      <td>97040.595682</td>\n\
              \      <td>48.743782</td>\n      <td>72.772392</td>\n      <td>61.520147</td>\n\
              \      <td>297.731881</td>\n    </tr>\n    <tr>\n      <th>F</th>\n  \
              \    <td>53.396229</td>\n      <td>61.694766</td>\n      <td>105989.116946</td>\n\
              \      <td>49.735712</td>\n      <td>72.041425</td>\n      <td>61.167210</td>\n\
              \      <td>297.852010</td>\n    </tr>\n  </tbody>\n</table>\n</div>",
            text/plain: "               fl       math    roll_number        sci    \
              \     sl         ss  \\\nregion                                      \
              \                                   \nA       54.156497  63.149551  105609.081674\
              \  50.432756  73.686377  62.453164   \nB       55.239836  63.638822  105746.142280\
              \  52.747653  74.455093  64.448891   \nC       54.080346  62.733572  124099.117879\
              \  50.344222  74.076716  64.647672   \nD       52.968296  62.589993  \
              \ 86303.811307  51.186670  73.665423  64.119590   \nE       52.085389\
              \  62.724153   97040.595682  48.743782  72.772392  61.520147   \nF   \
              \    53.396229  61.694766  105989.116946  49.735712  72.041425  61.167210\
              \   \n\n             total  \nregion              \nA       303.789099\
              \  \nB       310.482572  \nC       305.822393  \nD       304.428818  \n\
              E       297.731881  \nF       297.852010  "}, execution_count: 7, metadata: {},
          output_type: execute_result}]}, {execution_count: 8, outputs: [{data: {text/html: "<div>\n\
              <style scoped>\n    .dataframe tbody tr th:only-of-type {\n        vertical-align:\
              \ middle;\n    }\n\n    .dataframe tbody tr th {\n        vertical-align:\
              \ top;\n    }\n\n    .dataframe thead th {\n        text-align: right;\n\
              \    }\n</style>\n<table border=\"1\" class=\"dataframe\">\n  <thead>\n\
              \    <tr style=\"text-align: right;\">\n      <th></th>\n      <th>extra</th>\n\
              \      <th>fl</th>\n      <th>math</th>\n      <th>roll_number</th>\n\
              \      <th>sci</th>\n      <th>sl</th>\n      <th>ss</th>\n      <th>total</th>\n\
              \    </tr>\n    <tr>\n      <th>region</th>\n      <th></th>\n      <th></th>\n\
              \      <th></th>\n      <th></th>\n      <th></th>\n      <th></th>\n\
              \      <th></th>\n      <th></th>\n    </tr>\n  </thead>\n  <tbody>\n\
              \    <tr>\n      <th>A</th>\n      <td>0.0</td>\n      <td>1970430.0</td>\n\
              \      <td>2297949.0</td>\n      <td>3844276182</td>\n      <td>1835248.0</td>\n\
              \      <td>2681742.0</td>\n      <td>2272858.0</td>\n      <td>11058227.0</td>\n\
              \    </tr>\n    <tr>\n      <th>B</th>\n      <td>0.0</td>\n      <td>2282731.0</td>\n\
              \      <td>2630638.0</td>\n      <td>4371651268</td>\n      <td>2180377.0</td>\n\
              \      <td>3078048.0</td>\n      <td>2663866.0</td>\n      <td>12835660.0</td>\n\
              \    </tr>\n    <tr>\n      <th>C</th>\n      <td>0.0</td>\n      <td>1689470.0</td>\n\
              \      <td>1960926.0</td>\n      <td>3879462524</td>\n      <td>1573559.0</td>\n\
              \      <td>2315490.0</td>\n      <td>2020563.0</td>\n      <td>9560008.0</td>\n\
              \    </tr>\n    <tr>\n      <th>D</th>\n      <td>0.0</td>\n      <td>1348255.0</td>\n\
              \      <td>1593729.0</td>\n      <td>2198158074</td>\n      <td>1303315.0</td>\n\
              \      <td>1875890.0</td>\n      <td>1632613.0</td>\n      <td>7753802.0</td>\n\
              \    </tr>\n    <tr>\n      <th>E</th>\n      <td>0.0</td>\n      <td>1290103.0</td>\n\
              \      <td>1553740.0</td>\n      <td>2404665961</td>\n      <td>1207286.0</td>\n\
              \      <td>1802936.0</td>\n      <td>1523731.0</td>\n      <td>7377796.0</td>\n\
              \    </tr>\n    <tr>\n      <th>F</th>\n      <td>0.0</td>\n      <td>1407578.0</td>\n\
              \      <td>1629112.0</td>\n      <td>2799596535</td>\n      <td>1313172.0</td>\n\
              \      <td>1902542.0</td>\n      <td>1615059.0</td>\n      <td>7867463.0</td>\n\
              \    </tr>\n  </tbody>\n</table>\n</div>", text/plain: "        extra\
              \         fl       math  roll_number        sci         sl  \\\nregion\
              \                                                                   \n\
              A         0.0  1970430.0  2297949.0   3844276182  1835248.0  2681742.0\
              \   \nB         0.0  2282731.0  2630638.0   4371651268  2180377.0  3078048.0\
              \   \nC         0.0  1689470.0  1960926.0   3879462524  1573559.0  2315490.0\
              \   \nD         0.0  1348255.0  1593729.0   2198158074  1303315.0  1875890.0\
              \   \nE         0.0  1290103.0  1553740.0   2404665961  1207286.0  1802936.0\
              \   \nF         0.0  1407578.0  1629112.0   2799596535  1313172.0  1902542.0\
              \   \n\n               ss       total  \nregion                      \
              \   \nA       2272858.0  11058227.0  \nB       2663866.0  12835660.0 \
              \ \nC       2020563.0   9560008.0  \nD       1632613.0   7753802.0  \n\
              E       1523731.0   7377796.0  \nF       1615059.0   7867463.0  "}, execution_count: 8,
          metadata: {}, output_type: execute_result}]}, {execution_count: null, outputs: []}]