vedang patel

ipl data analysis

Everyone has IPL opinion about who wins the match, many says that match winning depends upon the toss winning so i have to do analysis on previous seasons data and tell that actually it is true? also i have to find that runs in match phases has impact on winning? Process first i did preprocessing then i went to solve Q1 that is about is toss winning impact on match winning? for that i created new column that is toss_match_winner to calculate win rate for both toss_match_winner and only_match_winner then i did further analysis that after winning toss the decision make impact on match winning and for that i ran an hypothesis test and came to conclusion. the i went for Q2 that is about match phase impact on match winning? for that first i do preprocess and create match_winner column to calculate winner team runs for every phase and then compare it with loser team after that i ran an hypothesis test to backup my solution and then came to conclusion. after that i went for Q3 that is about to find top5 batter and bowlers across 5 seasos so i do calculation. Results Toss winners win just 51.5% of matches but teams that win the toss and choose to field win 54.7%, while those who choose to bat win only 45.4%. The toss doesn't win matches. The decision does. Death overs show the largest run rate gap between winners and losers across all three phases confirmed by the most extreme p value (1.99e-112). The team that dominates the final 5 overs almost always wins. Reflection everyone does analysis and create charst that doesn't mean that answer is true but for that i do hypothesis test to backup my solution