#code begins here

#importing relevent libraries

import numpy as np

import pandas as pd

import matplotlib . pyplot as plt

#reading the given xlsx file (after converting it into .csv type) into a panda dataframe

datapandas=pd.read_table('swachhbharat.csv', delimiter=',')

#creating a numpy array using the above panda dataframe

datanumpy=datapandas.values

#extracting the rows that contain the relevent data of UP

#which are from row number 5617 to 6437

#the reading in array starts from 0, hence we take out 1 from the actual row number,

#ie, (5617-1)=5616 and (6437-1)=6436

#in python, the code datanumpy[x:y,z] extracts the rows AFTER x and till y of column z

#hence, we subtract 1 from the the first row number to include x, which is (5617-1)-1 = 5615

dataTotalV=datanumpy[5615:6436,4]

#dataTotalV = data of total number of villages

dataTotalODF=datanumpy[5615:6436,5]

#dataTotalODF = data of total number of ODF villages

#defining an array to store the fraction of villages that are ODF per district

dataFractionVODF=np.zeros(821,dtype=float)

#the size of the array is equal to the number of districts in UP, i.e., 6437-5617+1=821

#running a while loop to store the relevant entries into the newly defined array

i=0

while(i<821):

    dataFractionVODF[i]=dataTotalODF[i]/dataTotalV[i]

#each district has atleast one village, so the denominator is never equal to zero

    i=i+1

#to calculate the mean of the sample

i=0

#initializing a function that stores the sum of all villages that are ODF, which is initially 0

sumODF=0

#entering a while loop to store the sum of all villages that are ODF in the sumODF function

while(i<821):

    sumODF=sumODF+dataFractionVODF[i]

    i=i+1

#dividing the final sum by the number of entities (districts) to get the mean of the sample

SampleMean=sumODF/821

#to calculate the variance of the sample

i=0

#initializing a function that stores the sum of the square of the difference between an entry 

#and the mean of all entries for all different entries

sumV=0

#entering a while loop to store the relevant data

while(i<821):

    sumV=sumV+((dataFractionVODF[i]-SampleMean)**(2))

#the syntax (x)**(y) for a function x and a constant y means the function x to the power y

    i=i+1

#dividing the final sum of squares by total entries minus one, as given in the formula,

#ie 821-1=820 to get the variance of the sample

SampleVariance=(sumV/820)

#taking the square-root of the variance of the sample to get the standard deviation of sample

SampleStandardD=((sumV/820)**(0.5))

#plotting the histogram of number of districts vs fraction of villages that are ODF

#taking the color of bars as orange, and the width of each bar equal to 95% of the actual width

#so as to leave a gap of width that is 5% of the original width of bar to separate the bars

plt.hist(dataFractionVODF, rwidth=0.95, color="orange")

#giving the plot a title

plt.title('The fraction of villages that are declared ODF in each district in UP')

#labeling the x and the y axis individually

plt.xlabel('Fraction of villages that are ODF')

plt.ylabel('Number of Districts')

#drawing the line for 'mean of sample' (vertically) of indigo color and width = 2 units

plt.axvline(SampleMean, color="indigo", linestyle='dashed', linewidth=2)

#drawing the line of 'standard deviation of sample' (horizontally) of blue color and width = 2

plt.axhline(SampleStandardD, color="blue", linestyle='dashed', linewidth=2)

#in the syntax axhline and axvline, 'ax' represent 'Axis' and 'h' and 'v' just after 'ax' 

#represent 'horizontal' and 'vertical' respectively

#labeling the 'mean of sample' line with appropriate name, coordinates and color

plt.text(SampleMean+0.02, 140, 'Mean of Sample', color='indigo')

#labeling the 'standard deviation of sample' line with appropriate name, coordinates and color

plt.text(SampleStandardD+0.79, -1, 'Standard Deviation of Sample', color='blue')

#printing the plot

plt.show()

#printing the values of the Mean, Variance and the Standard Deviation of the sample separately

print("The Sample Mean is", SampleMean)

print("The Sample Variance is", SampleVariance) 

print("The Sample Standard Deviation is", SampleStandardD)

#code ends here