# -*- coding: utf-8 -*-
#-----(1) data analysis of agriculture sector -----

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import random

df = pd.read_csv ('C:/Users/Jeet Das/Desktop/Major Project - Indian Economy/Project ( Section 1-Indian Economy)/Section-1_Data_sheet/(02)_agriculture.csv',encoding="cp1252")

print("\n------- output data :-----------\n")
print("Agriculture data analysis:")
print("\n-----------------------------------\n")

# Question – A : get row and column numbers 

print('---------------------------------------------')
print("Dimension of the data frame = ",df.shape)
print('---------------------------------------------')

# Question – B : print column names :


print('------------------------\n Column names as follows :')
print('------------------------\n')
count = 0
for col in df.columns: 
        print(count,"-->",col)
        count = count+1
print("\n-----------------------------\n")

#Question – C : State_Name (using GROUP BY method) and no. of states :

state_names = df.groupby(['State_Name'])[['District_Name']].count()
print("---------------------------------")
print("\t states names : ")
print("-------------------------------")
print(state_names)
print("-------------------------------")
count = 0
for row in range(len(state_names)): 
        count = count+1
print("total no. of states = ",count)        
print("-----------------------------\n")

#Question – 1 : Andaman and Nicobar Islands(Detailed analysis) :

print("\n--- State-1: Andaman and Nicobar Islands(Detailed analysis) :-------")
df_andaman = df[df.State_Name == 'Andaman and Nicobar Islands']
df_andaman_dist = df_andaman.groupby(['District_Name'])[['Crop_Year']].count()
print(df_andaman_dist)

print("-----------------------------")
count = 0
for row in range(len(df_andaman_dist)): 
        count = count+1
print("total no. of district in [State-1] Andaman and Nicobar Islands = ",count)        
print("-----------------------------\n")

# crop year in Andaman and Nicobar Islands

print("------ Crop year in Andaman and Nicobar Islands --------")
df_andaman_year = df_andaman.groupby(['Crop_Year'])[['Crop_Year']].count()
print(df_andaman_year)

# crop types in Andaman and Nicobar Islands

print("----- Crop types in Andaman and Nicobar Islands --------")
df_andaman_crop = df_andaman.groupby(['Crop'])[['Crop']].count()
print(df_andaman_crop)

# details of Andaman( [1] Nicobars)

print("------ Details of Andaman( [1] Nicobars) -----------------")
df_andaman_1 = df_andaman[df_andaman.District_Name == 'NICOBARS']

# finding sum of year =( 2000,2001,2002,2003,2004,2005,2006,2010 )

print("---------------------------------")
print("Sum for Crop_Year = 2000")
print("---------------------------------")
df_andaman_1_2000 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2000,'Area':'Production']
df_andaman_1_2000_sum = df_andaman_1_2000.sum(axis = 0, skipna = True)
print(df_andaman_1_2000_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2001")
print("---------------------------------")
df_andaman_1_2001 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2001,'Area':'Production']
df_andaman_1_2001_sum = df_andaman_1_2001.sum(axis = 0, skipna = True)
print(df_andaman_1_2001_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2002")
print("---------------------------------")
df_andaman_1_2002 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2002,'Area':'Production'] 
df_andaman_1_2002_sum = df_andaman_1_2002.sum(axis = 0, skipna = True)
print(df_andaman_1_2002_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2003")
print("---------------------------------")
df_andaman_1_2003 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2003,'Area':'Production'] 
df_andaman_1_2003_sum = df_andaman_1_2003.sum(axis = 0, skipna = True)
print(df_andaman_1_2003_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2004")
print("---------------------------------")
df_andaman_1_2004 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2004,'Area':'Production'] 
df_andaman_1_2004_sum = df_andaman_1_2004.sum(axis = 0, skipna = True)
print(df_andaman_1_2004_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2005")
print("---------------------------------")
df_andaman_1_2005 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2005,'Area':'Production']
df_andaman_1_2005_sum = df_andaman_1_2005.sum(axis = 0, skipna = True)
print(df_andaman_1_2005_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2006")
print("---------------------------------")
df_andaman_1_2006 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2006,'Area':'Production'] 
df_andaman_1_2006_sum = df_andaman_1_2006.sum(axis = 0, skipna = True)
print(df_andaman_1_2006_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2010")
print("---------------------------------")
df_andaman_1_2010 = df_andaman_1.loc[df_andaman_1['Crop_Year'] == 2010,'Area':'Production'] 
df_andaman_1_2010_sum = df_andaman_1_2010.sum(axis = 0, skipna = True)
print(df_andaman_1_2010_sum)
print("---------------------------------")


# details of Andaman( [2] NORTH AND MIDDLE ANDAMAN )

print("------ Details of Andaman( [2] NORTH AND MIDDLE ANDAMAN )-----------")
df_andaman_2 = df_andaman[df_andaman.District_Name == 'NORTH AND MIDDLE ANDAMAN']

# finding sum of year =( 2000,2001,2002,2003,2004,2005,2006,2010 )

print("---------------------------------")
print("Sum for Crop_Year = 2000")
print("---------------------------------")
df_andaman_2_2000 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2000,'Area':'Production'] 
df_andaman_2_2000_sum = df_andaman_2_2000.sum(axis = 0, skipna = True)
print(df_andaman_2_2000_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2001")
print("---------------------------------")
df_andaman_2_2001 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2001,'Area':'Production'] 
df_andaman_2_2001_sum = df_andaman_2_2001.sum(axis = 0, skipna = True)
print(df_andaman_2_2001_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2002")
print("---------------------------------")
df_andaman_2_2002 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2002,'Area':'Production'] 
df_andaman_2_2002_sum = df_andaman_2_2002.sum(axis = 0, skipna = True)
print(df_andaman_2_2002_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2003")
print("---------------------------------")
df_andaman_2_2003 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2003,'Area':'Production'] 
df_andaman_2_2003_sum = df_andaman_2_2003.sum(axis = 0, skipna = True)
print(df_andaman_2_2003_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2004")
print("---------------------------------")
df_andaman_2_2004 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2004,'Area':'Production'] 
df_andaman_2_2004_sum = df_andaman_2_2004.sum(axis = 0, skipna = True)
print(df_andaman_2_2004_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2005")
print("---------------------------------")
df_andaman_2_2005 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2005,'Area':'Production'] 
df_andaman_2_2005_sum = df_andaman_2_2005.sum(axis = 0, skipna = True)
print(df_andaman_2_2005_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2006")
print("---------------------------------")
df_andaman_2_2006 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2006,'Area':'Production'] 
df_andaman_2_2006_sum = df_andaman_2_2006.sum(axis = 0, skipna = True)
print(df_andaman_2_2006_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2010")
print("---------------------------------")
df_andaman_2_2010 = df_andaman_2.loc[df_andaman_2['Crop_Year'] == 2010,'Area':'Production'] 
df_andaman_2_2010_sum = df_andaman_2_2010.sum(axis = 0, skipna = True)
print(df_andaman_2_2010_sum)
print("---------------------------------")

# details of Andaman( [3] SOUTH ANDAMANS )

print("----- Details of Andaman( [3] SOUTH ANDAMANS )-------")
df_andaman_3 = df_andaman[df_andaman.District_Name == 'SOUTH ANDAMANS']

# finding sum of year =( 2000,2001,2002,2003,2004,2005,2006,2010 )

print("---------------------------------")
print("Sum for Crop_Year = 2000")
print("---------------------------------")
df_andaman_3_2000 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2000,'Area':'Production']
df_andaman_3_2000_sum = df_andaman_3_2000.sum(axis = 0, skipna = True)
print(df_andaman_3_2000_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2001")
print("---------------------------------")
df_andaman_3_2001 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2001,'Area':'Production']
df_andaman_3_2001_sum = df_andaman_3_2001.sum(axis = 0, skipna = True)
print(df_andaman_3_2001_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2002")
print("---------------------------------")
df_andaman_3_2002 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2002,'Area':'Production']
df_andaman_3_2002_sum = df_andaman_3_2002.sum(axis = 0, skipna = True)
print(df_andaman_3_2002_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2003")
print("---------------------------------")
df_andaman_3_2003 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2003,'Area':'Production']
df_andaman_3_2003_sum = df_andaman_3_2003.sum(axis = 0, skipna = True)
print(df_andaman_3_2003_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2004")
print("---------------------------------")
df_andaman_3_2004 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2004,'Area':'Production']
df_andaman_3_2004_sum = df_andaman_3_2004.sum(axis = 0, skipna = True)
print(df_andaman_3_2004_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2005")
print("---------------------------------")
df_andaman_3_2005 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2005,'Area':'Production']
df_andaman_3_2005_sum = df_andaman_3_2005.sum(axis = 0, skipna = True)
print(df_andaman_3_2005_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2006")
print("---------------------------------")
df_andaman_3_2006 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2006,'Area':'Production']
df_andaman_3_2006_sum = df_andaman_3_2006.sum(axis = 0, skipna = True)
print(df_andaman_3_2006_sum)
print("---------------------------------")
print("Sum for Crop_Year = 2010")
print("---------------------------------")
df_andaman_3_2010 = df_andaman_3.loc[df_andaman_3['Crop_Year'] == 2010,'Area':'Production']
df_andaman_3_2010_sum = df_andaman_3_2010.sum(axis = 0, skipna = True)
print(df_andaman_3_2010_sum)
print("---------------------------------")

# plotting of Andaman( [1] Nicobars) 'Area' and 'Production' 

x = ('2000','2001','2002','2003','2004','2005','2006','2010')

y1 = (df_andaman_1_2000_sum['Area'],
      df_andaman_1_2001_sum['Area'], 
      df_andaman_1_2002_sum['Area'],
      df_andaman_1_2003_sum['Area'],
      df_andaman_1_2004_sum['Area'],
      df_andaman_1_2005_sum['Area'],
      df_andaman_1_2006_sum['Area'],
      df_andaman_1_2010_sum['Area'])

y2 = (df_andaman_1_2000_sum['Production'],
      df_andaman_1_2001_sum['Production'], 
      df_andaman_1_2002_sum['Production'],
      df_andaman_1_2003_sum['Production'],
      df_andaman_1_2004_sum['Production'],
      df_andaman_1_2005_sum['Production'],
      df_andaman_1_2006_sum['Production'],
      df_andaman_1_2010_sum['Production'])                                      

plt.subplot(121)
plt.title('State-1 : Andaman( [1] Nicobars) (Area)')
plt.xlabel('year -->')
plt.ylabel('area -->')                                                                      
plt.plot(x,y1)
plt.show

plt.subplot(122)
plt.title('State-1 : Andaman( [1] Nicobars) (production )')
plt.xlabel('year -->')
plt.ylabel('production -->')
plt.plot(x,y2)
plt.show()

# plotting of Andaman( [2] NORTH AND MIDDLE ANDAMAN ) 'Area' and 'Production' 

x = ('2000','2001','2002','2003','2004','2005','2006','2010')

y1 = (df_andaman_2_2000_sum['Area'],
      df_andaman_2_2001_sum['Area'], 
      df_andaman_2_2002_sum['Area'],
      df_andaman_2_2003_sum['Area'],
      df_andaman_2_2004_sum['Area'],
      df_andaman_2_2005_sum['Area'],
      df_andaman_2_2006_sum['Area'],
      df_andaman_2_2010_sum['Area'])

y2 = (df_andaman_2_2000_sum['Production'],
      df_andaman_2_2001_sum['Production'], 
      df_andaman_2_2002_sum['Production'],
      df_andaman_2_2003_sum['Production'],
      df_andaman_2_2004_sum['Production'],
      df_andaman_2_2005_sum['Production'],
      df_andaman_2_2006_sum['Production'],
      df_andaman_2_2010_sum['Production'])                                      

plt.subplot(121)
plt.title('State-1 : Andaman( [2] NORTH AND MIDDLE ANDAMAN)(Area)')
plt.xlabel('year -->')
plt.ylabel('area -->')                                                                      
plt.plot(x,y1)
plt.show

plt.subplot(122)
plt.title('State-1 : Andaman( [2] NORTH AND MIDDLE ANDAMAN ) (production)')
plt.xlabel('year -->')
plt.ylabel('production -->')
plt.plot(x,y2)
plt.show()

# plotting of  Andaman( [3] SOUTH ANDAMANS ) 'Area' and 'Production' 

x = ('2000','2001','2002','2003','2004','2005','2006','2010')

y1 = (df_andaman_3_2000_sum['Area'],
      df_andaman_3_2001_sum['Area'], 
      df_andaman_3_2002_sum['Area'],
      df_andaman_3_2003_sum['Area'],
      df_andaman_3_2004_sum['Area'],
      df_andaman_3_2005_sum['Area'],
      df_andaman_3_2006_sum['Area'],
      df_andaman_3_2010_sum['Area'])

y2 = (df_andaman_3_2000_sum['Production'],
      df_andaman_3_2001_sum['Production'], 
      df_andaman_3_2002_sum['Production'],
      df_andaman_3_2003_sum['Production'],
      df_andaman_3_2004_sum['Production'],
      df_andaman_3_2005_sum['Production'],
      df_andaman_3_2006_sum['Production'],
      df_andaman_3_2010_sum['Production'])                                      

plt.subplot(121)
plt.title('State-1 :  Andaman( [3] SOUTH ANDAMANS ) (Area)')
plt.xlabel('year -->')
plt.ylabel('area -->')                                                                      
plt.plot(x,y1)
plt.show

plt.subplot(122)
plt.title('State-1 :  Andaman( [3] SOUTH ANDAMANS )(production )')
plt.xlabel('year -->')
plt.ylabel('production -->')
plt.plot(x,y2)
plt.show()