#install the required libraries
!pip install pandas
!pip install numpy
!pip install matplotlib


#Import the necessary libraries
import pandas as pd
import numpy as np
#Loading the dataset and printing first five rows of the dataset
df = pd.read_csv("https://github.com/jainharshit27/datasets/raw/main/IPL%20Player%20Stats%20-%202016%20till%202019.csv")
display(df)

#Finding data is for how many tournaments. (on running first line it is clear that data is of 2017,2018 and 2019). We kepts data of 2019 only by running the second line.
df.Tournament.unique()
df=df.loc[df['Tournament'] == 'IPL 2019']
display(df)


#Kept the necessary columns/ features from the dataset
newdf = df.filter(['Team','Player','Batting Innings','Batting Average','Bowling Innings','Bowling Average'], axis=1)
display(newdf)

#Replaced '-' values with 0. (This is required as when we will apply a filter say runs>0, in this case only numeric values can be compaired so - is changed to 0)
newdf=newdf.replace('-', '0')
display(newdf)

#Checking the datatype of each columns, and changing them to numeric data type.
newdf.dtypes
newdf[['Batting Innings','Batting Average','Bowling Innings','Bowling Average']] = newdf[['Batting Innings','Batting Average','Bowling Innings','Bowling Average']].apply(pd.to_numeric)
newdf.dtypes

#Keeping the players who have played the given number of bolwing and batting innings to fnd the allrounders
Allrounder=newdf[(newdf['Batting Innings'] > 6)  & (newdf['Bowling Innings'] > 6) ]
display(Allrounder)

#Plotting The batting avg. of allrounders
Allrounder.plot.bar(x='Player',y='Batting Average',colormap='spring')

#Plottign the bowling avg. of the allrounders
Allrounder.plot.bar(x='Player',y='Bowling Average',colormap='Paired')