# -*- coding: utf-8 -*-
"""
Created on Tue Mar 22 23:08:45 2022

@author: juju0
"""

mport numpy as np
import pandas as pd
import seaborn as sb
import matplotlib as plt

"""Student 1:"""

#a)

jobinmumbai= Problem[Problem["Location"].astype("str").str.contains("Mumbai")]

'''There are 3731 jobs in Mumbai'''

#b)

metroscities = ["Bengaluru", "Kolkata", "Delhi", "Chennai", "Gurgaon", "Pune"]

metro_jobss = 0
for i in metroscities:
    metro_jobss = metro_jobss + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]
metro_jobss

list = ["Bengaluru", "Kolkata", "Delhi", "Chennai", "Gurgaon", "Pune"]
bengaluru_jobs = 0
kolkata_jobs = 0
delhi_jobs = 0
chennai_jobs = 0
gurgaon_jobs = 0
pune_jobs = 0
for i in list:
    if (i == "Bengaluru"): 
        bengaluru_jobs = bengaluru_jobs + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]
    if (i == "Kolkata"): 
        kolkata_jobs = kolkata_jobs + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]
    if (i == "Delhi"): 
        delhi_jobs = delhi_jobs + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]
    if (i == "Chennai"): 
        chennai_jobs = chennai_jobs + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]
    if (i == "Gurgaon"): 
        gurgaon_jobs = gurgaon_jobs + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]
    if (i == "Pune"): 
        pune_jobs = pune_jobs + Problem[Problem["Location"].astype("str").str.contains(i)].shape[0]

'''
bengaluru_jobs 
5529

kolkata_jobs 
373

delhi_jobs 
1834

chennai_jobs 
1518

gurgaon_jobs 
2770

pune_jobs
1781

metro_jobs
13805
'''        
#Student 2

#a)
sb.displot(Problem["Experience"], kind = "hist")        
sb.histplot(Problem["Experience"], kde = True)

#Due to a high number of unique values, the x axis is not distinguishable

new = pd.value_counts(Problem.Experience).reset_index()
new.columns = ["Experience", "Frequency"]
top5 = new.iloc[0:5,:]

import matplotlib.pyplot as plt
plt.bar(top5.Experience, top5.Frequency, color = "yellow")

#The bar chart shows the years of experience that the majority openings require#

"""
  Experience  Frequency
0   5-10 yrs       1274
1    2-5 yrs       1188
2    3-8 yrs        922
3    2-7 yrs        832
4    4-9 yrs        678
"""
#Manually modifying the dataframe in variable explorer
#to sort ascending values of Experience

fresher_jobs = new.iloc[0:6, :]

"""
   Experience  Frequency
38    0-0 yrs        151
26    0-1 yrs        296
21    0-2 yrs        386
28    0-3 yrs        269
39    0-4 yrs        130
"""

total_fresher_jobs = sum(fresher_jobs.Frequency)

"""There are 1653 total fresher jobs"""