##code begins here

##importing relevant libraries 

import numpy as np

import pandas as pd

import matplotlib . pyplot as plt

##creating a numpy array and reading the xls file into this array

##first we read the data file into a pandas dataframe and then create a numpy array using

##this dataframe

datapandas=pd.read_table('assign1.csv', delimiter=',')

datanumpy=datapandas.values

##We next extract the columns of the array which give us the number of male teachers and 

##number of female teachers per pre-primary school 

dataMteachers=datanumpy[:,13]

dataFteachers=datanumpy[:,14]

dataNschools=datanumpy[:,12]

##getting the total number of teachers per pre-primary school

dataTteachers=np.add(dataMteachers,dataFteachers)

##appending this into the old array to get the modified array

datafinal=np.c_[datanumpy,dataTteachers]

##Since we must plot histograms for rural,urban and total separately, we create

##3 arrays to carry out this task 

datarural=np.zeros(35,dtype=float)

dataurban=np.zeros(35,dtype=float)

datatotal=np.zeros(35,dtype=float)

##and now we use a while loop to add required elements to these arrays

##(notice that the total number of teachers across India, which is not needed for 

##the histograms is omitted by carefully selecting the size of these new arrays )

i=0

while (i<35):

    if(dataNschools[3*i]!=0):      

        datarural[i]=dataTteachers[3*i]/dataNschools[3*i]

##some states have a value of 0 for dataNschools, hence the if condition

    else:

         datarural[i]=0

    if(dataNschools[(3*i)+1]!=0): 

        dataurban[i]=dataTteachers[(3*i)+1]/dataNschools[(3*i)+1]

    else:

         datarural[i]=0   

    if(dataNschools[(3*i)+2]!=0): 

          datatotal[i]=dataTteachers[(3*i)+2]/dataNschools[(3*i)+2]

    else:

        datarural[i]=0  

    i=i+1 

##before plotting the histograms, we must first select a good range. 

## We set the range from the arrays minimum to its maximum .

##We now plot histograms for all three arrays. First, for rural

plt.hist(datarural,bins=[0,1,2,3,4,5,6],range=(min(datarural),max(datarural)),rwidth=0.95)

plt.title('Distribution of Pre-primary teachers in India (in rural areas) across states'  )

plt.xlabel('number of teachers per school')

plt.ylabel('number of states')

plt.show()

##now urban

plt.hist(dataurban,bins=[0,1,2,3,4,5,6,7,8,9,10,11,12],range=(min(dataurban),max(dataurban)), color="green",rwidth=0.95)

plt.title('Distribution of Pre-primary teachers in India (in urban areas) across states'  )

plt.xlabel('number of teachers per school')

plt.ylabel('number of states')

##and finally total

plt.show()

plt.hist(datatotal,bins=[0,1,2,3,4,5,6],range=(min(datatotal),max(datatotal)), color="purple",rwidth=0.95)

plt.title('Distribution of Pre-primary teachers in India (total) across states'  )

plt.xlabel('number of teachers per school')

plt.ylabel('number of states')

plt.show()

##end of code