Player Performance Estimation using AI Collaborative Filtering

1. Introduction

Often times before crucial matches, or in general, we would like to know the performance of a batsman against a bowler or vice-versa, but we may not have the data. We generally have data where different batsmen would have faced different sets of bowlers with certain performance data like ballsFaced, totalRuns, fours, sixes, strike rate and timesOut. Similarly different bowlers would have performance figures(deliveries, runsConceded, economyRate and wicketTaken) against different sets of batsmen. We will never have the data for all batsmen against all bowlers. However, it would be good estimate the performance of batsmen against a bowler, even though we do not have the performance data. This could be done using collaborative filtering which identifies and computes based on the similarity between batsmen vs bowlers & bowlers vs batsmen.

This post shows an approach whereby we can estimate a batsman’s performance against bowlers even though the batsman may not have faced those bowlers, based on his/her performance against other bowlers. It also estimates the performance of bowlers against batsmen using the same approach. This is based on the recommender algorithm which is used to recommend products to customers based on their rating on other products.

This idea came to me while generating the performance of batsmen vs bowlers & vice-versa for 2 IPL teams in this IPL 2022 with my Shiny app GooglyPlusPlus in the optimization tab, I found that there were some batsmen for which there was no data against certain bowlers, probably because they are playing for the first time in their team or because they were new (see picture below)

In the picture above there is no data for Dewald Brevis against Jasprit Bumrah and YS Chahal. Wouldn’t be great to estimate the performance of Brevis against Bumrah or vice-versa? Can we estimate this performance?

While pondering on this problem, I realized that this problem formulation is similar to the problem formulation for the famous Netflix movie recommendation problem, in which user’s ratings for certain movies are known and based on these ratings, the recommender engine can generate ratings for movies not yet seen.

This post estimates a player’s (batsman/bowler) using the recommender engine This post is based on R package recommenderlab

“Michael Hahsler (2021). recommenderlab: Lab for Developing and Testing Recommender Algorithms. R package version 0.2-7. https://github.com/mhahsler/recommenderlab

Note 1: Thw data for this analysis is taken from Cricsheet after being processed by my R package yorkr.

You can also read this post in RPubs at Player Performance Estimation using AI Collaborative Filtering

A PDF copy of this post is available at Player Performance Estimation using AI Collaborative Filtering.pdf

You can download this R Markdown file and the associated data and perform the analysis yourself using any other recommender engine from Github at playerPerformanceEstimation

Problem statement

In the table below we see a set of bowlers vs a set of batsmen and the number of times the bowlers got these batsmen out.
By knowing the performance of the bowlers against some of the batsmen we can use collaborative filter to determine the missing values. This is done using the recommender engine.

The Recommender Engine works as follows. Let us say that there are feature vectors x^1, x^2 and x^3 for the 3 bowlers which identify the characteristics of these bowlers (“fast”, “lateral drift through the air”, “movement off the pitch”). Let each batsman be identified by parameter vectors \theta^1, \theta^2 and so on

For e.g. consider the following table

Then by assuming an initial estimate for the parameter vector \theta and the feature vector xx we can formulate this as an optimization problem which tries to minimize the error for \theta^T*x This can work very well as the algorithm can determine features which cannot be captured. So for e.g. some particular bowler may have very impressive figures. This could be due to some aspect of the bowling which cannot be captured by the data for e.g. let’s say the bowler uses the ‘scrambled seam’ when he is most effective, with a slightly different arc to the flight. Though the algorithm cannot identify the feature as we know it, but the ML algorithm should pick up intricacies which cannot be captured in data.

Hence the algorithm can be quite effective.

Note: The recommender lab performance is not very good and the Mean Square Error is quite high. Also, the ROC and AUC curves show that not in aLL cases the algorithm is doing a clean job of separating the True positives (TPR) from the False Positives (FPR)

Note: This is similar to the recommendation problem

The collaborative optimization object can be considered as a minimization of both \theta and the features x and can be written as

J(x^{(1)},x^{(2)},..x^{(n_{u})}, \theta^{(1)},\theta^{(2)},..,\theta^{(n_{m})}}= 1/2\sum(\theta^{j})^{T}x^{i}- y^{(i,j)})^{2} + \lambda\sum\sum (x_{k}^{i})^{2} + \lambda\sum\sum (_\theta{k}^{j})^{2}

The collaborative filtering algorithm can be summarized as follows

  1. Initialize \theta^1, \theta^2\theta^{n_{u}} and the set of features be x^1,x^2, … ,x^{n_{m}} to small random values
  2. Minimize J(\theta^1, \theta^2\theta^{n_{u}},x^1, x^2, … ,x^{n_{m}}) using gradient descent. For every
    j=1,2, …n_{u}, i= 1,2,.., n_{m}
  3. x_{k}^{i} := x_{k}^{i}\alpha ( \sigma (\theta^j)^T)x^iy^(i,j)\theta_{k}^{j} + \lambda x_{k}^i

    &

    \theta_{k}^{i} := \theta_{k}^{i}\alpha ( \sigma (\theta^j)^T)x^i - y^(i,j)\theta_{k}^{j} + \lambda x_{k}^i
  4. Hence for a batsman with parameters \theta and a bowler with (learned) features x, predict the “times out” for the player where the value is not known using \theta^Tx

The above derivation for the recommender problem is taken from Machine Learning by Prof Andrew Ng at Coursera from the lecture Collaborative filtering

There are 2 main types of Collaborative Filtering(CF) approaches

  1. User based Collaborative Filtering User-based CF is a memory-based algorithm which tries to mimics word-of-mouth by analyzing rating data from many individuals. The assumption is that users with similar preferences will rate items similarly.
  2. Item based Collaborative Filtering Item-based CF is a model-based approach which produces recommendations based on the relationship between items inferred from the rating matrix. The assumption behind this approach is that users will prefer items that are similar to other items they like.

1a. A note on ROC and Precision-Recall curves

A small note on interpreting ROC & Precision-Recall curves in the post below

ROC Curve: The ROC curve plots the True Positive Rate (TPR) against the False Positive Rate (FPR). Ideally the TPR should increase faster than the FPR and the AUC (area under the curve) should be close to 1

Precision-Recall: The precision-recall curve shows the tradeoff between precision and recall for different threshold. A high area under the curve represents both high recall and high precision, where high precision relates to a low false positive rate, and high recall relates to a low false negative rate

library(reshape2)
library(dplyr)
library(ggplot2)
library(recommenderlab)
library(tidyr)
load("recom_data/batsmenVsBowler20_22.rdata")

2. Define recommender lab helper functions

Helper functions for the RMarkdown notebook are created

  • eval – Gives details of RMSE, MSE and MAE of ML algorithm
  • evalRecomMethods – Evaluates different recommender methods and plot the ROC and Precision-Recall curves
# This function returns the error for the chosen algorithm and also predicts the estimates
# for the given data
eval <- function(data, train1, k1,given1,goodRating1,recomType1="UBCF"){
  set.seed(2022)
  e<- evaluationScheme(data,
                       method = "split",
                       train = train1,
                       k = k1,
                       given = given1,
                       goodRating = goodRating1)
  
  r1 <- Recommender(getData(e, "train"), recomType1)
  print(r1)
  
  p1 <- predict(r1, getData(e, "known"), type="ratings")
  print(p1)
  
  error = calcPredictionAccuracy(p1, getData(e, "unknown"))
  
  print(error)
  p2 <- predict(r1, data, type="ratingMatrix")
  p2
}
# This function will evaluate the different recommender algorithms and plot the AUC and ROC curves
evalRecomMethods <- function(data,k1,given1,goodRating1){
  set.seed(2022)
  e<- evaluationScheme(data,
                       method = "cross",
                       k = k1,
                       given = given1,
                       goodRating = goodRating1)
  
  models_to_evaluate <- list(
    `IBCF Cosinus` = list(name = "IBCF", 
                          param = list(method = "cosine")),
    `IBCF Pearson` = list(name = "IBCF", 
                          param = list(method = "pearson")),
    `UBCF Cosinus` = list(name = "UBCF",
                          param = list(method = "cosine")),
    `UBCF Pearson` = list(name = "UBCF",
                          param = list(method = "pearson")),
    `Zufälliger Vorschlag` = list(name = "RANDOM", param=NULL)
  )
  
  n_recommendations <- c(1, 5, seq(10, 100, 10))
  list_results <- evaluate(x = e, 
                           method = models_to_evaluate, 
                           n = n_recommendations)
  plot(list_results, annotate=c(1,3), legend="bottomright")
  plot(list_results, "prec/rec", annotate=3, legend="topleft")
}

3. Batsman performance estimation

The section below regenerates the performance for batsmen based on incomplete data for the different fields in the data frame namely balls faced, fours, sixes, strike rate, times out. The recommender lab allows one to test several different algorithms all at once namely

  1. User based – Cosine similarity method, Pearson similarity
  2. Item based – Cosine similarity method, Pearson similarity
  3. Popular
  4. Random
  5. SVD and a few others

3a. Batting dataframe

head(df)
##   batsman1         bowler1 ballsFaced totalRuns fours sixes  SR timesOut
## 1 A Badoni        A Mishra          0         0     0     0 NaN        0
## 2 A Badoni        A Nortje          0         0     0     0 NaN        0
## 3 A Badoni         A Zampa          0         0     0     0 NaN        0
## 4 A Badoni     Abdul Samad          0         0     0     0 NaN        0
## 5 A Badoni Abhishek Sharma          0         0     0     0 NaN        0
## 6 A Badoni      AD Russell          0         0     0     0 NaN        0

3b Data set and data preparation

For this analysis the data from Cricsheet has been processed using my R package yorkr to obtain the following 2 data sets – batsmenVsBowler – This dataset will contain the performance of the batsmen against the bowler and will capture a) ballsFaced b) totalRuns c) Fours d) Sixes e) SR f) timesOut – bowlerVsBatsmen – This data set will contain the performance of the bowler against the difference batsmen and will include a) deliveries b) runsConceded c) EconomyRate d) wicketsTaken

Obviously many rows/columns will be empty

This is a large data set and hence I have filtered for the period > Jan 2020 and < Dec 2022 which gives 2 datasets a) batsmanVsBowler20_22.rdata b) bowlerVsBatsman20_22.rdata

I also have 2 other datasets of all batsmen and bowlers in these 2 dataset in the files c) all-batsmen20_22.rds d) all-bowlers20_22.rds

You can download the data and this RMarkdown notebook from Github at PlayerPerformanceEstimation

Feel free to download and analyze the data and use any recommendation engine you choose

3c. Exploratory analysis

Initially an exploratory analysis is done on the data

df3 <- select(df, batsman1,bowler1,timesOut)
df6 <- xtabs(timesOut ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
print(df8[1:10,1:10])
##                 A Mishra A Nortje A Zampa Abdul Samad Abhishek Sharma
## A Badoni              NA       NA      NA          NA              NA
## A Manohar             NA       NA      NA          NA              NA
## A Nortje              NA       NA      NA          NA              NA
## AB de Villiers        NA        4       3          NA              NA
## Abdul Samad           NA       NA      NA          NA              NA
## Abhishek Sharma       NA       NA      NA          NA              NA
## AD Russell             1       NA      NA          NA              NA
## AF Milne              NA       NA      NA          NA              NA
## AJ Finch              NA       NA      NA          NA               3
## AJ Tye                NA       NA      NA          NA              NA
##                 AD Russell AF Milne AJ Tye AK Markram Akash Deep
## A Badoni                NA       NA     NA         NA         NA
## A Manohar               NA       NA     NA         NA         NA
## A Nortje                NA       NA     NA         NA         NA
## AB de Villiers           3       NA      3         NA         NA
## Abdul Samad             NA       NA     NA         NA         NA
## Abhishek Sharma         NA       NA     NA         NA         NA
## AD Russell              NA       NA      6         NA         NA
## AF Milne                NA       NA     NA         NA         NA
## AJ Finch                NA       NA     NA         NA         NA
## AJ Tye                  NA       NA     NA         NA         NA

The dots below represent data for which there is no performance data. These cells need to be estimated by the algorithm

set.seed(2022)
r <- as(df8,"realRatingMatrix")
getRatingMatrix(r)[1:15,1:15]
## 15 x 15 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 15 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                               
## A Badoni         . . . . . . . . . . . . . . .
## A Manohar        . . . . . . . . . . . . . . .
## A Nortje         . . . . . . . . . . . . . . .
## AB de Villiers   . 4 3 . . 3 . 3 . . . 4 3 . .
## Abdul Samad      . . . . . . . . . . . . . . .
## Abhishek Sharma  . . . . . . . . . . . 1 . . .
## AD Russell       1 . . . . . . 6 . . . 3 3 3 .
## AF Milne         . . . . . . . . . . . . . . .
## AJ Finch         . . . . 3 . . . . . . 1 . . .
## AJ Tye           . . . . . . . . . . . 1 . . .
## AK Markram       . . . 3 . . . . . . . . . . .
## AM Rahane        9 . . . . 3 . 3 . . . 3 3 . .
## Anmolpreet Singh . . . . . . . . . . . . . . .
## Anuj Rawat       . . . . . . . . . . . . . . .
## AR Patel         . . . . . . . 1 . . . . . . .
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:15,1:15]
## 15 x 15 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 15 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                              
## AB de Villiers  . 4 3 . . 3 . 3 . . . 4 3 . .
## Abdul Samad     . . . . . . . . . . . . . . .
## Abhishek Sharma . . . . . . . . . . . 1 . . .
## AD Russell      1 . . . . . . 6 . . . 3 3 3 .
## AJ Finch        . . . . 3 . . . . . . 1 . . .
## AM Rahane       9 . . . . 3 . 3 . . . 3 3 . .
## AR Patel        . . . . . . . 1 . . . . . . .
## AT Rayudu       2 . . . . . 1 . . . . 3 . . .
## B Kumar         3 . 3 . . . . . . . . . . 3 .
## BA Stokes       . . . . . . 3 4 . . . 3 . . .
## CA Lynn         . . . . . . . 9 . . . 3 . . .
## CH Gayle        . . . . . 6 . 3 . . . 6 . . .
## CH Morris       . 3 . . . . . . . . . 3 . . .
## D Padikkal      . 4 . . . 3 . . . . . . 3 . .
## DA Miller       . . . . . 3 . . . . . 3 . . .
# Get the summary of the data
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   3.000   3.000   3.463   4.000  21.000
# Normalize the data
r0_m <- normalize(r0)
getRatingMatrix(r0_m)[1:15,1:15]
## 15 x 15 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 15 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                                                       
## AB de Villiers   .         -0.7857143 -1.7857143 .  .       -1.7857143
## Abdul Samad      .          .          .         .  .        .        
## Abhishek Sharma  .          .          .         .  .        .        
## AD Russell      -2.6562500  .          .         .  .        .        
## AJ Finch         .          .          .         . -0.03125  .        
## AM Rahane        4.6041667  .          .         .  .       -1.3958333
## AR Patel         .          .          .         .  .        .        
## AT Rayudu       -2.1363636  .          .         .  .        .        
## B Kumar          0.3636364  .          0.3636364 .  .        .        
## BA Stokes        .          .          .         .  .        .        
## CA Lynn          .          .          .         .  .        .        
## CH Gayle         .          .          .         .  .        1.5476190
## CH Morris        .          0.3500000  .         .  .        .        
## D Padikkal       .          0.6250000  .         .  .       -0.3750000
## DA Miller        .          .          .         .  .       -0.7037037
##                                                                              
## AB de Villiers   .         -1.7857143 . . . -0.7857143 -1.785714  .         .
## Abdul Samad      .          .         . . .  .          .         .         .
## Abhishek Sharma  .          .         . . . -1.6000000  .         .         .
## AD Russell       .          2.3437500 . . . -0.6562500 -0.656250 -0.6562500 .
## AJ Finch         .          .         . . . -2.0312500  .         .         .
## AM Rahane        .         -1.3958333 . . . -1.3958333 -1.395833  .         .
## AR Patel         .         -2.3333333 . . .  .          .         .         .
## AT Rayudu       -3.1363636  .         . . . -1.1363636  .         .         .
## B Kumar          .          .         . . .  .          .         0.3636364 .
## BA Stokes       -0.6086957  0.3913043 . . . -0.6086957  .         .         .
## CA Lynn          .          5.3200000 . . . -0.6800000  .         .         .
## CH Gayle         .         -1.4523810 . . .  1.5476190  .         .         .
## CH Morris        .          .         . . .  0.3500000  .         .         .
## D Padikkal       .          .         . . .  .         -0.375000  .         .
## DA Miller        .          .         . . . -0.7037037  .         .         .

4. Create a visual representation of the rating data before and after the normalization

The histograms show the bias in the data is removed after normalization

r0=r[(m=rowCounts(r) > 10),]
getRatingMatrix(r0)[1:15,1:10]
## 15 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                    
## AB de Villiers  . 4 3 . . 3 . 3 . .
## Abdul Samad     . . . . . . . . . .
## Abhishek Sharma . . . . . . . . . .
## AD Russell      1 . . . . . . 6 . .
## AJ Finch        . . . . 3 . . . . .
## AM Rahane       9 . . . . 3 . 3 . .
## AR Patel        . . . . . . . 1 . .
## AT Rayudu       2 . . . . . 1 . . .
## B Kumar         3 . 3 . . . . . . .
## BA Stokes       . . . . . . 3 4 . .
## CA Lynn         . . . . . . . 9 . .
## CH Gayle        . . . . . 6 . 3 . .
## CH Morris       . 3 . . . . . . . .
## D Padikkal      . 4 . . . 3 . . . .
## DA Miller       . . . . . 3 . . . .
#Plot ratings
image(r0, main = "Raw Ratings")
#Plot normalized ratings
r0_m <- normalize(r0)
getRatingMatrix(r0_m)[1:15,1:15]
## 15 x 15 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 15 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                                                       
## AB de Villiers   .         -0.7857143 -1.7857143 .  .       -1.7857143
## Abdul Samad      .          .          .         .  .        .        
## Abhishek Sharma  .          .          .         .  .        .        
## AD Russell      -2.6562500  .          .         .  .        .        
## AJ Finch         .          .          .         . -0.03125  .        
## AM Rahane        4.6041667  .          .         .  .       -1.3958333
## AR Patel         .          .          .         .  .        .        
## AT Rayudu       -2.1363636  .          .         .  .        .        
## B Kumar          0.3636364  .          0.3636364 .  .        .        
## BA Stokes        .          .          .         .  .        .        
## CA Lynn          .          .          .         .  .        .        
## CH Gayle         .          .          .         .  .        1.5476190
## CH Morris        .          0.3500000  .         .  .        .        
## D Padikkal       .          0.6250000  .         .  .       -0.3750000
## DA Miller        .          .          .         .  .       -0.7037037
##                                                                              
## AB de Villiers   .         -1.7857143 . . . -0.7857143 -1.785714  .         .
## Abdul Samad      .          .         . . .  .          .         .         .
## Abhishek Sharma  .          .         . . . -1.6000000  .         .         .
## AD Russell       .          2.3437500 . . . -0.6562500 -0.656250 -0.6562500 .
## AJ Finch         .          .         . . . -2.0312500  .         .         .
## AM Rahane        .         -1.3958333 . . . -1.3958333 -1.395833  .         .
## AR Patel         .         -2.3333333 . . .  .          .         .         .
## AT Rayudu       -3.1363636  .         . . . -1.1363636  .         .         .
## B Kumar          .          .         . . .  .          .         0.3636364 .
## BA Stokes       -0.6086957  0.3913043 . . . -0.6086957  .         .         .
## CA Lynn          .          5.3200000 . . . -0.6800000  .         .         .
## CH Gayle         .         -1.4523810 . . .  1.5476190  .         .         .
## CH Morris        .          .         . . .  0.3500000  .         .         .
## D Padikkal       .          .         . . .  .         -0.375000  .         .
## DA Miller        .          .         . . . -0.7037037  .         .         .
image(r0_m, main = "Normalized Ratings")
set.seed(1234)
hist(getRatings(r0), breaks=25)
hist(getRatings(r0_m), breaks=25)

4a. Data for analysis

The data frame of the batsman vs bowlers from the period 2020 -2022 is read as a dataframe. To remove rows with very low number of ratings(timesOut, SR, Fours, Sixes etc), the rows are filtered so that there are at least more 10 values in the row. For the player estimation the dataframe is converted into a wide-format as a matrix (m x n) of batsman x bowler with each of the columns of the dataframe i.e. timesOut, SR, fours or sixes. These different matrices can be considered as a rating matrix for estimation.

A similar approach is taken for estimating bowler performance. Here a wide form matrix (m x n) of bowler x batsman is created for each of the columns of deliveries, runsConceded, ER, wicketsTaken

5. Batsman’s times Out

The code below estimates the number of times the batsmen would lose his/her wicket to the bowler. As discussed in the algorithm above, the recommendation engine will make an initial estimate features for the bowler and an initial estimate for the parameter vector for the batsmen. Then using gradient descent the recommender engine will determine the feature and parameter values such that the over Mean Squared Error is minimum

From the plot for the different algorithms it can be seen that UBCF performs the best. However the AUC & ROC curves are not optimal and the AUC> 0.5

df3 <- select(df, batsman1,bowler1,timesOut)
df6 <- xtabs(timesOut ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
# Filter only rows where the row count is > 10
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                    
## AB de Villiers  . 4 3 . . 3 . 3 . .
## Abdul Samad     . . . . . . . . . .
## Abhishek Sharma . . . . . . . . . .
## AD Russell      1 . . . . . . 6 . .
## AJ Finch        . . . . 3 . . . . .
## AM Rahane       9 . . . . 3 . 3 . .
## AR Patel        . . . . . . . 1 . .
## AT Rayudu       2 . . . . . 1 . . .
## B Kumar         3 . 3 . . . . . . .
## BA Stokes       . . . . . . 3 4 . .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   3.000   3.000   3.463   4.000  21.000
# Evaluate the different plotting methods
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
#Evaluate the error
a=eval(r0[1:dim(r0)[1]],0.8,k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 70 users.
## 18 x 145 rating matrix of class 'realRatingMatrix' with 1755 ratings.
##     RMSE      MSE      MAE 
## 2.069027 4.280872 1.496388
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
m=as(c,"data.frame")
names(m) =c("batsman","bowler","TimesOut")

6. Batsman’s Strike rate

This section deals with the Strike rate of batsmen versus bowlers and estimates the values for those where the data is incomplete using UBCF method.

Even here all the algorithms do not perform too efficiently. I did try out a few variations but could not lower the error (suggestions welcome!!)

df3 <- select(df, batsman1,bowler1,SR)
df6 <- xtabs(SR ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                                                           
## AB de Villiers   96.8254 171.4286  33.33333  . 66.66667 223.07692   .     
## Abdul Samad       .      228.0000   .        .  .       100.00000   .     
## Abhishek Sharma 150.0000   .        .        .  .        66.66667   .     
## AD Russell      111.4286   .        .        .  .         .         .     
## AJ Finch        250.0000 116.6667   .        . 50.00000  85.71429 112.5000
## AJ Tye            .        .        .        .  .         .       100.0000
## AK Markram        .        .        .       50  .         .         .     
## AM Rahane       121.1111   .        .        .  .       113.82979 117.9487
## AR Patel        183.3333   .      200.00000  .  .       433.33333   .     
## AT Rayudu       126.5432 200.0000 122.22222  .  .       105.55556   .     
##                                
## AB de Villiers  109.52381 .   .
## Abdul Samad       .       .   .
## Abhishek Sharma   .       .   .
## AD Russell      195.45455 .   .
## AJ Finch          .       .   .
## AJ Tye            .       .   .
## AK Markram        .       .   .
## AM Rahane        33.33333 . 200
## AR Patel        171.42857 .   .
## AT Rayudu       204.76190 .   .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   5.882  85.714 116.667 128.529 160.606 600.000
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
a=eval(r0[1:dim(r0)[1]],0.8, k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 105 users.
## 27 x 145 rating matrix of class 'realRatingMatrix' with 3220 ratings.
##       RMSE        MSE        MAE 
##   77.71979 6040.36508   58.58484
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
n=as(c,"data.frame")
names(n) =c("batsman","bowler","SR")

7. Batsman’s Sixes

The snippet of code estimes the sixes of the batsman against bowlers. The ROC and AUC curve for UBCF looks a lot better here, as it significantly greater than 0.5

df3 <- select(df, batsman1,bowler1,sixes)
df6 <- xtabs(sixes ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                      
## AB de Villiers  3 3 . . . 18 .  3 . .
## AD Russell      3 . . . .  . . 12 . .
## AJ Finch        2 . . . .  . .  . . .
## AM Rahane       7 . . . .  3 1  . . .
## AR Patel        4 . 3 . .  6 .  1 . .
## AT Rayudu       5 2 . . .  . .  1 . .
## BA Stokes       . . . . .  . .  . . .
## CA Lynn         . . . . .  . .  9 . .
## CH Gayle       17 . . . . 17 .  . . .
## CH Morris       . . 3 . .  . .  . . .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00    3.00    3.00    4.68    6.00   33.00
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
## Timing stopped at: 0.003 0 0.002
a=eval(r0[1:dim(r0)[1]],0.8, k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 52 users.
## 14 x 145 rating matrix of class 'realRatingMatrix' with 1634 ratings.
##      RMSE       MSE       MAE 
##  3.529922 12.460350  2.532122
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
o=as(c,"data.frame")
names(o) =c("batsman","bowler","Sixes")

8. Batsman’s Fours

The code below estimates 4s for the batsmen

df3 <- select(df, batsman1,bowler1,fours)
df6 <- xtabs(fours ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                      
## AB de Villiers   . 1 . . . 24 . 3 . .
## Abhishek Sharma  . . . . .  . . . . .
## AD Russell       1 . . . .  . . 9 . .
## AJ Finch         . 1 . . .  3 2 . . .
## AK Markram       . . . . .  . . . . .
## AM Rahane       11 . . . .  8 7 . . 3
## AR Patel         . . . . .  . . 3 . .
## AT Rayudu       11 2 3 . .  6 . 6 . .
## BA Stokes        1 . . . .  . . . . .
## CA Lynn          . . . . .  . . 6 . .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   3.000   4.000   6.339   9.000  55.000
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
## Timing stopped at: 0.008 0 0.008
## Warning in .local(x, method, ...): 
##   Recommender 'UBCF Pearson' has failed and has been removed from the results!
a=eval(r0[1:dim(r0)[1]],0.8, k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 67 users.
## 17 x 145 rating matrix of class 'realRatingMatrix' with 2083 ratings.
##      RMSE       MSE       MAE 
##  5.486661 30.103447  4.060990
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
p=as(c,"data.frame")
names(p) =c("batsman","bowler","Fours")

9. Batsman’s Total Runs

The code below estimates the total runs that would have scored by the batsman against different bowlers

df3 <- select(df, batsman1,bowler1,totalRuns)
df6 <- xtabs(totalRuns ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                          
## A Badoni         .  . . . .   . .   . . .
## A Manohar        .  . . . .   . .   . . .
## A Nortje         .  . . . .   . .   . . .
## AB de Villiers  61 36 3 . 6 261 .  69 . .
## Abdul Samad      . 57 . . .  12 .   . . .
## Abhishek Sharma  3  . . . .   6 .   . . .
## AD Russell      39  . . . .   . . 129 . .
## AF Milne         .  . . . .   . .   . . .
## AJ Finch        15  7 . . 3  18 9   . . .
## AJ Tye           .  . . . .   . 4   . . .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00    9.00   24.00   41.36   54.00  452.00
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given1=7,goodRating1=median(getRatings(r0)))
a=eval(r0[1:dim(r0)[1]],0.8, k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 105 users.
## 27 x 145 rating matrix of class 'realRatingMatrix' with 3256 ratings.
##       RMSE        MSE        MAE 
##   41.50985 1723.06788   29.52958
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
q=as(c,"data.frame")
names(q) =c("batsman","bowler","TotalRuns")

10. Batsman’s Balls Faced

The snippet estimates the balls faced by batsmen versus bowlers

df3 <- select(df, batsman1,bowler1,ballsFaced)
df6 <- xtabs(ballsFaced ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Mishra', 'A Nortje', 'A Zampa' ... ]]
##                                         
## A Badoni         .  . . . .   . .  . . .
## A Manohar        .  . . . .   . .  . . .
## A Nortje         .  . . . .   . .  . . .
## AB de Villiers  63 21 9 . 9 117 . 63 . .
## Abdul Samad      . 25 . . .  12 .  . . .
## Abhishek Sharma  2  . . . .   9 .  . . .
## AD Russell      35  . . . .   . . 66 . .
## AF Milne         .  . . . .   . .  . . .
## AJ Finch         6  6 . . 6  21 8  . . .
## AJ Tye           .  . . . .   9 4  . . .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00    9.00   18.00   30.21   39.00  384.00
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
a=eval(r0[1:dim(r0)[1]],0.8, k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 112 users.
## 28 x 145 rating matrix of class 'realRatingMatrix' with 3378 ratings.
##       RMSE        MSE        MAE 
##   33.91251 1150.05835   23.39439
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
r=as(c,"data.frame")
names(r) =c("batsman","bowler","BallsFaced")

11. Generate the Batsmen Performance Estimate

This code generates the estimated dataframe with known and ‘predicted’ values

a1=merge(m,n,by=c("batsman","bowler"))
a2=merge(a1,o,by=c("batsman","bowler"))
a3=merge(a2,p,by=c("batsman","bowler"))
a4=merge(a3,q,by=c("batsman","bowler"))
a5=merge(a4,r,by=c("batsman","bowler"))
a6= select(a5, batsman,bowler,BallsFaced,TotalRuns,Fours, Sixes, SR,TimesOut)
head(a6)
##          batsman          bowler BallsFaced TotalRuns Fours Sixes  SR TimesOut
## 1 AB de Villiers        A Mishra         94       124     7     5 144        5
## 2 AB de Villiers        A Nortje         26        42     4     3 148        3
## 3 AB de Villiers         A Zampa         28        42     5     7 106        4
## 4 AB de Villiers Abhishek Sharma         22        28     0    10 136        5
## 5 AB de Villiers      AD Russell         70       135    14    12 207        4
## 6 AB de Villiers        AF Milne         31        45     6     6 130        3

12. Bowler analysis

Just like the batsman performance estimation we can consider the bowler’s performances also for estimation. Consider the following table

As in the batsman analysis, for every batsman a set of features like (“strong backfoot player”, “360 degree player”,“Power hitter”) can be estimated with a set of initial values. Also every bowler will have an associated parameter vector θθ. Different bowlers will have performance data for different set of batsmen. Based on the initial estimate of the features and the parameters, gradient descent can be used to minimize actual values {for e.g. wicketsTaken(ratings)}.

load("recom_data/bowlerVsBatsman20_22.rdata")

12a. Bowler dataframe

Inspecting the bowler dataframe

head(df2)
##    bowler1        batsman1 balls runsConceded       ER wicketTaken
## 1 A Mishra        A Badoni     0            0 0.000000           0
## 2 A Mishra       A Manohar     0            0 0.000000           0
## 3 A Mishra        A Nortje     0            0 0.000000           0
## 4 A Mishra  AB de Villiers    63           61 5.809524           0
## 5 A Mishra     Abdul Samad     0            0 0.000000           0
## 6 A Mishra Abhishek Sharma     2            3 9.000000           0
names(df2)
## [1] "bowler1"      "batsman1"     "balls"        "runsConceded" "ER"          
## [6] "wicketTaken"

13. Balls bowled by bowler

The below section estimates the balls bowled for each bowler. We can see that UBCF Pearson and UBCF Cosine both perform well

df3 <- select(df2, bowler1,batsman1,balls)
df6 <- xtabs(balls ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Badoni', 'A Manohar', 'A Nortje' ... ]]
##                                          
## A Mishra        . . .  63  .  2 35 .  6 .
## A Nortje        . . .  21 25  .  . .  6 .
## A Zampa         . . .   9  .  .  . .  . .
## Abhishek Sharma . . .   9  .  .  . .  6 .
## AD Russell      . . . 117 12  9  . . 21 9
## AF Milne        . . .   .  .  .  . .  8 4
## AJ Tye          . . .  63  .  . 66 .  . .
## Akash Deep      . . .   .  .  .  . .  . .
## AR Patel        . . . 188  5  1 84 . 29 5
## Arshdeep Singh  . . .   6  6 24 18 . 12 .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00    9.00   18.00   29.61   36.00  384.00
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
a=eval(r0[1:dim(r0)[1]],0.8,k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 96 users.
## 24 x 195 rating matrix of class 'realRatingMatrix' with 3954 ratings.
##      RMSE       MSE       MAE 
##  30.72284 943.89294  19.89204
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
s=as(c,"data.frame")
names(s) =c("bowler","batsman","BallsBowled")

14. Runs conceded by bowler

This section estimates the runs conceded by the bowler. The UBCF Cosinus algorithm performs the best with TPR increasing fastewr than FPR

df3 <- select(df2, bowler1,batsman1,runsConceded)
df6 <- xtabs(runsConceded ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Badoni', 'A Manohar', 'A Nortje' ... ]]
##                                            
## A Mishra        . . .  61  .  3  41 . 15  .
## A Nortje        . . .  36 57  .   . .  8  .
## A Zampa         . . .   3  .  .   . .  .  .
## Abhishek Sharma . . .   6  .  .   . .  3  .
## AD Russell      . . . 276 12  6   . . 21  .
## AF Milne        . . .   .  .  .   . . 10  4
## AJ Tye          . . .  69  .  . 138 .  .  .
## Akash Deep      . . .   .  .  .   . .  .  .
## AR Patel        . . . 205  5  . 165 . 33 13
## Arshdeep Singh  . . .  18  3 51  51 .  6  .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##    1.00    9.00   24.00   41.34   54.00  458.00
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
## Timing stopped at: 0.004 0 0.004
## Warning in .local(x, method, ...): 
##   Recommender 'UBCF Pearson' has failed and has been removed from the results!
a=eval(r0[1:dim(r0)[1]],0.8,k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 95 users.
## 24 x 195 rating matrix of class 'realRatingMatrix' with 3820 ratings.
##       RMSE        MSE        MAE 
##   43.16674 1863.36749   30.32709
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
t=as(c,"data.frame")
names(t) =c("bowler","batsman","RunsConceded")

15. Economy Rate of the bowler

This section computes the economy rate of the bowler. The performance is not all that good

df3 <- select(df2, bowler1,batsman1,ER)
df6 <- xtabs(ER ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Badoni', 'A Manohar', 'A Nortje' ... ]]
##                                                                       
## A Mishra        . . .  5.809524  .     9.00  7.028571 . 15.000000  .  
## A Nortje        . . . 10.285714 13.68  .     .        .  8.000000  .  
## A Zampa         . . .  2.000000  .     .     .        .  .         .  
## Abhishek Sharma . . .  4.000000  .     .     .        .  3.000000  .  
## AD Russell      . . . 14.153846  6.00  4.00  .        .  6.000000  .  
## AF Milne        . . .  .         .     .     .        .  7.500000  6.0
## AJ Tye          . . .  6.571429  .     .    12.545455 .  .         .  
## Akash Deep      . . .  .         .     .     .        .  .         .  
## AR Patel        . . .  6.542553  6.00  .    11.785714 .  6.827586 15.6
## Arshdeep Singh  . . . 18.000000  3.00 12.75 17.000000 .  3.000000  .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##  0.3529  5.2500  7.1126  7.8139  9.8000 36.0000
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
## Timing stopped at: 0.003 0 0.004
## Warning in .local(x, method, ...): 
##   Recommender 'UBCF Pearson' has failed and has been removed from the results!
a=eval(r0[1:dim(r0)[1]],0.8,k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 95 users.
## 24 x 195 rating matrix of class 'realRatingMatrix' with 3839 ratings.
##      RMSE       MSE       MAE 
##  4.380680 19.190356  3.316556
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
u=as(c,"data.frame")
names(u) =c("bowler","batsman","EconomyRate")

16. Wickets Taken by bowler

The code below computes the wickets taken by the bowler versus different batsmen

df3 <- select(df2, bowler1,batsman1,wicketTaken)
df6 <- xtabs(wicketTaken ~ ., df3)
df7 <- as.data.frame.matrix(df6)
df8 <- data.matrix(df7)
df8[df8 == 0] <- NA
r <- as(df8,"realRatingMatrix")
r0=r[(rowCounts(r) > 10),]
getRatingMatrix(r0)[1:10,1:10]
## 10 x 10 sparse Matrix of class "dgCMatrix"
##    [[ suppressing 10 column names 'A Badoni', 'A Manohar', 'A Nortje' ... ]]
##                                   
## A Mishra       . . . . . . 1 . . .
## A Nortje       . . . 4 . . . . . .
## A Zampa        . . . 3 . . . . . .
## AD Russell     . . . 3 . . . . . .
## AJ Tye         . . . 3 . . 6 . . .
## AR Patel       . . . 4 . 1 3 . 1 1
## Arshdeep Singh . . . 3 . . 3 . . .
## AS Rajpoot     . . . . . . 3 . . .
## Avesh Khan     . . . . . . 1 . 3 .
## B Kumar        . . . 9 . . 3 . 1 .
summary(getRatings(r0))
##    Min. 1st Qu.  Median    Mean 3rd Qu.    Max. 
##   1.000   3.000   3.000   3.423   3.000  21.000
evalRecomMethods(r0[1:dim(r0)[1]],k1=5,given=7,goodRating1=median(getRatings(r0)))
## Timing stopped at: 0.003 0 0.003
## Warning in .local(x, method, ...): 
##   Recommender 'UBCF Pearson' has failed and has been removed from the results!
a=eval(r0[1:dim(r0)[1]],0.8,k1=5,given1=7,goodRating1=median(getRatings(r0)),"UBCF")
## Recommender of type 'UBCF' for 'realRatingMatrix' 
## learned using 64 users.
## 16 x 195 rating matrix of class 'realRatingMatrix' with 1908 ratings.
##     RMSE      MSE      MAE 
## 2.672677 7.143203 1.956934
b=round(as(a,"matrix")[1:10,1:10])
c <- as(b,"realRatingMatrix")
v=as(c,"data.frame")
names(v) =c("bowler","batsman","WicketTaken")

17. Generate the Bowler Performance estmiate

The entire dataframe is regenerated with known and ‘predicted’ values

r1=merge(s,t,by=c("bowler","batsman"))
r2=merge(r1,u,by=c("bowler","batsman"))
r3=merge(r2,v,by=c("bowler","batsman"))
r4= select(r3,bowler, batsman, BallsBowled,RunsConceded,EconomyRate, WicketTaken)
head(r4)
##     bowler         batsman BallsBowled RunsConceded EconomyRate WicketTaken
## 1 A Mishra  AB de Villiers         102          144           8           4
## 2 A Mishra     Abdul Samad          13           20           7           4
## 3 A Mishra Abhishek Sharma          14           26           8           2
## 4 A Mishra      AD Russell          47           85           9           3
## 5 A Mishra        AJ Finch          45           61          11           4
## 6 A Mishra          AJ Tye          14           20           5           4

18. Conclusion

This post showed an approach for performing the Batsmen Performance Estimate & Bowler Performance Estimate. The performance of the recommender engine could have been better. In any case, I think this approach will work for player estimation provided the recommender algorithm is able to achieve a high degree of accuracy. This will be a good way to estimate as the algorithm will be able to determine features and nuances of batsmen and bowlers which cannot be captured by data.

References

  1. Recommender Systems – Machine Learning by Prof Andrew Ng
  2. recommenderlab: A Framework for Developing and Testing Recommendation Algorithms
  3. ROC 
  4. Precision-Recall

Also see

  1. Big Data 7: yorkr waltzes with Apache NiFi
  2. Benford’s law meets IPL, Intl. T20 and ODI cricket
  3. Using Linear Programming (LP) for optimizing bowling change or batting lineup in T20 cricket
  4. IPL 2022: Near real-time analytics with GooglyPlusPlus!!!
  5. Sixer
  6. Introducing cricpy:A python package to analyze performances of cricketers
  7. The Clash of the Titans in Test and ODI cricket
  8. Cricketr adds team analytics to its repertoire!!!
  9. Informed choices through Machine Learning – Analyzing Kohli, Tendulkar and Dravid
  10. Big Data 6: The T20 Dance of Apache NiFi and yorkpy

To see all posts click Index of posts

GooglyPlusPlus2022 optimizes batting/bowling lineup

GooglyPlusPlus2022 is the new avatar of last year’s GooglyPlusPlus2021. Roughly, about 5 years back I had written a post on Using linear programming to optimize T20 batting and bowling line up. This post has been on the back of my mind for a long time and I decided to pay this post a revisit. This requires computing performance of individual batsmen vs bowlers and vice-versa for performing the optimization. So in this latest incarnation, there are 4 new functions

  1. batsmanVsBowlerPerf – Performance of batsmen against chosen bowlers
  2. bowlerVsBatsmanPerf – Performance of bowlers versus specific batsmen
  3. battingOptimization – Optimizing batting line up based on strike rates ad remaining overs
  4. bowlingOptimization – Optimizing bowling line up based on economy rates and remaining overs

These 4 functions have been incorporated in all the supported 9 T20 formats namely a. IPL b. Intl. T20(men) c. Intl. T20 (women) d. BBL e. NTB f. PSL g. WBB h. CPL i. SSM

Check out GooglyPlusPlus2022!!

You can clone/fork the code for GooglyPlusPlus2022 from Github from gpp2022-1

With this latest update you can do a myriad of analyses of batsmen, bowlers, teams, matches. This is just-in-time for the IPL Mega-auction!! Do check out these other posts of GooglyPlusPlus for other detailed analysis

  1. GooglyPlusPlus2021: Towards more picturesque analytics!
  2. GooglyPlusPlus2021 now with power play, middle and death over analysis
  3. GooglyPlusPlus2021 adds new bells and whistles!!
  4. GooglyPlusPlus2021 is now fully interactive!!!

A) Batsman Vs Bowlers – This option computes the performance of individual batsman against individual bowlers

a) IPL Batsmen vs Bowlers

Included below are the performances of Dhoni, Raina and Kohli against Malinga, Ashwin and Bumrah. Note: The last 2 text box input are not required for this.

b) Intl. T20 (men) Batsmen vs Bowlers

Note: You can type the name and choose from the drop down list

B) Bowler vs Batsmen – You can check the performance of specific bowlers against specific batsmen

a) Intl. T20 (women) India vs Australia

b) PSL Bowlers vs Batsmen

C) Strategy for optimizing batting and bowling line up

From the above 2 tabs, it is obvious, that different bowlers have different ER and wicket rate against different batsmen. In other words, the effectiveness of the bowlers varies by batsmen. Conversely, batsmen are more comfortable with certain bowlers versus others and this shows up in different strike rates.

Hence during the death overs, when trying to restrict batsmen to a certain score or on the flip side when the batting side needs to score a target within certain overs, we need to take advantage of the relative effectiveness of bowlers vs batsmen for optimising bowling and aggressiveness of batsmen versus bowlers to quickly reach the target.

This is the approach that is used for bowling and batting optimisation. For optimising bowling, we need to formulate a minimisation problem based on ER rates and for optimising batting, a maximisation strategy is chosen based on SR. ‘Integer programming’ is used to compute during the last set of overs

This latest version includes optimization using “integer programming” based on R package lpSolve.

Here are the 2 formulations

Assume there are 3 bowlers – bwlr_{1},bwlr_{2},bwlr_{3}
and there are 3 batsmen – bman_{1},bman_{2},bman_{3}

I) LP Formulation for bowling order

Let the economy rate er_{ij} be the Economy Rate of the jth bowler to the ith batsman. Also if remaining overs for the bowlers are o_{1},o_{2},o_{3}
and the total number of overs left to be bowled are
o_{1}+o_{2}+o_{3} = N

Let the economy rate er_{ij} be the Economy Rate of the jth bowler to the ith batsman.
Objective function : Minimize –
er_{11}*o_{11} + er_{12}*o_{12} +..+er_{1n}*o_{1n}+ er_{21}*o_{21} + er_{22}*o_{22}+.. + er_{22}*o_{2n}+ er_{m1}*o_{m1}+..+ er_{mn}*o_{mn}
i.e.
\sum_{i=1}^{i=m}\sum_{j=1}^{i=n}er_{ij}*o_{ij}
Constraints
Where o_{j} is the number of overs remaining for the jth bowler against  ‘k’ batsmen
o_{j1} + o_{j2} + .. o_{jk} < o_{j}
and if the total number of overs remaining to be bowled is N then
o_{1} + o_{2} +...+ o_{k} = N or
\sum_{j=1}^{j=k} o_{j} =N
The overs that any bowler can bowl is o_{j} >=0

II) LP Formulation for batting lineup

Let the strike rate sr_{ij}  be the Strike Rate of the ith batsman to the jth bowler
Objective function : Maximize –
sr_{11}*o_{11} + sr_{12}*o_{12} +..+ sr_{1n}*o_{1n}+ sr_{21}*o_{21} + sr_{22}*o_{22}+.. sr_{2n}*o_{2n}+ sr_{m1}*o_{m1}+..+ sr_{mn}*o_{mn}
i.e.
\sum_{i=1}^{i=4}\sum_{j=1}^{i=3}sr_{ij}*o_{ij}
Constraints
Where o_{j} is the number of overs remaining for the jth bowler against  ‘k’ batsmen
o_{j1} + o_{j2} + .. o_{jk} < o_{j}
and the total number of overs remaining to be bowled is N then
o_{1} + o_{2} +...+ o_{k} = N or
\sum_{j=1}^{j=k} o_{j} =N
The overs that any bowler can bowl is
o_{j} >=0

C) Optimized bowling lineup

a) IPL – Optimizing bowling line up

Note: For computing the Optimal bowling lineup, the total number of overs remaining and the number of overs for each bowler have to be entered.

b) PSL – Optimizing batting line up

d) Optimized batting lineup

a) Intl. T20 (men) India vs England

b) Carribean Premier LeagueOptimizing batting line up

Give GooglyPlusPlus2022 a spin!

You can also check the code here gpp2022-1

Hope you have a good time with GooglyPlusPlus2022!

Also see

  1. Re-working the Lucy Richardson algorithm in OpenCV
  2. Deconstructing Convolutional Neural Networks with Tensorflow and Keras
  3. Deep Learning from first principles in Python, R and Octave – Part 5
  4. Cricketr adds team analytics to its repertoire!!!
  5. Practical Machine Learning with R and Python – Part 4
  6. Cricpy takes a swing at the ODIs
  7. yorkpy takes a hat-trick, bowls out Intl. T20s, BBL and Natwest T20!!!
  8. Big Data-4: Webserver log analysis with RDDs, Pyspark, SparkR and SparklyR
  9. Introducing QCSimulator: A 5-qubit quantum computing simulator in R

To see all posts click Index of posts

More player analysis with gganimate()

This post continues the analysis of IPL and T20 (men) batsmen and bowlers through animated charts. In my last post Analyzing player performance with animated charts! I had used animated horizontal bars to display the totalRuns or totalWickets over a 3 year ‘sliding window’. While that was cool, the only drawback of that animation was the batsman and bowler performance was measured in a single dimension of either total(mean) runs or total(mean) wickets.

I think to fairly describe batsmen and bowlers we need at least the following 2 attributes

  • Runs and Strike rate for batsmen and
  • Wickets and Economy rate for bowlers

So, I have created new animation charts which use these attributes for batsmen and bowlers.

The animated charts are

  • Based on a sliding window of 3 years (Jan 2008- Dec 2010, Jan 2009-Dec 2010,…, Jan 2019-Dec 2021)
  • I have taken the top 10 percentile and sometimes the top 5 percentile of batsmen and bowlers to keep the charts more manageable
  • The charts are based on gganimate().

Note 1: I tried several options for the animation before settling on this one. The animation may seem a bit jerky but, we can follow the progress of players more easily through the years

Note 2: Some charts may display points, without the corresponding names. I think this may be because the animation tries to create intermediate points between the charts.

Note 3: For fine-grained, but static analysis across different intervals or seasons, checkout my my posts GooglyPlusPlus2021 now with power play, middle and death over analysis and GooglyPlusPlus2021: Towards more picturesque analytics!

The code for the animation can be cloned from Github at animation2. Feel free to modify the parameters for a different animation behavior.

Here are performances of IPL and T20 (men) players. Note all charts are based on a 3 year staggered window. The Top 10 percentile is considered

  1. Runs vs SR – IPL

We can that Shikhar Dhawan is a top performer for 4 years from 2018-2021. He definitely deserved a slot in the India WC 15 member squad.

2. Wickets vs ER – IPL

Similarly, YS Chahal also deserved a slot in the 15 member sqad

3. Runs vs SR in Power play – IPL

S Dhawan, De Kock & KL Rahul are the best players in Power play

4. Runs vs Strike rate in Middle overs – IPL

Rishabh Pant, Shreyas Iyer,Sanju Samson and KL Rahul are best performers in Middle overs

5.Runs vs SR in Death overs – IPL

It is MS Dhoni all the way, till Hardik Pandya catches up. But H Pandya had poor IPL seasons in 2020, 2021. See my post GooglyPlusPlus2021: Towards more picturesque analytics! for finer analysis

6. Wickets vs ER in Power play – IPL

In the early years B. Kumar led. More recently D Chahar and T Boult

7. Wickets vs ER in Middle overs – IPL

YS Chahal, Rashid Khan, Imran Tahir and Rahul Chahar lead in Middle overs

8. Wickets vs ER in Death overs – IPL

Bumrah & Rabada top performers

9. Runs vs SR – T20 (men)

Babar Azam, PR Stirling, Rohit Sharma, S Dhawan, KL Rahul are best performers in recent times

10. Wickets vs ER – T20 (men)

Wanindu Hasaranga, T Shamsi, Shadab Khan, Rashid Khan, T Boult are best performers in recent times

11. Runs vs SR in Power Play – T20 (men)

PR Stirling, RG Sharma, C Munro, Shikhar Dhawan lead

12. Runs vs SR in Middle overs – T20 (men)

Babar Azam, followed by Kohli, S Dhawan, Rizwan, RG Sharma in recent years

13. Runs vs SR in Death overs – T20 (men)

Shoaib Malik, V Kohli, Mohamed Nabi. Mohammed Rizwan and other top the death overs

14. Wickets vs ER in Power play (T20 men)

TG Southee, Mujeeb Ur Rahman and B Stanlake lead in recent years

15. Wickets vs ER in Middle overs – T20 (men)

Top bowlers are Shadab Khan, T Shamsi, Kuldeep Yadav, YS Chahal and AC Agar

16. Wickets vs ER in Death overs – T20 (men)

Haris Rauf, AJ Tye, Rashid Khan and Chris Jordan excel in death overs

You may also like

  1. Re-introducing cricketr! : An R package to analyze performances of cricketers
  2. Cricketr adds team analytics to its repertoire!!!
  3. Pitching yorkpy … short of good length to IPL – Part 1
  4. yorkr rocks women’s One Day International (ODI) and International T20!!
  5. Big Data-5: kNiFi-ing through cricket data with yorkpy
  6. Using Linear Programming (LP) for optimizing bowling change or batting lineup in T20 cricket
  7. Introducing cricpy:A python package to analyze performances of cricketers
  8. Benford’s law meets IPL, Intl. T20 and ODI cricket
  9. GooglyPlusPlus2021 is now fully interactive!!!
  10. Sixer – R package cricketr’s new Shiny avatar

To see all posts click Index of posts

GooglyPlusPlus2021 now with power play, middle and death over analysis

This latest edition of GooglyPlusPlus2021 now includes detailed analysis of teams, batsmen and bowlers in power play, middle and death overs. The T20 format is based on 3 phases as each side faces 20 overs.

Power play: Overs: 0 – 6 – No more than 2 players can be outside the 30 yard circle

Middle overs: Overs: 7- 16 – During these overs the batting side tries to consolidate their innings

Death overs: Overs: 16 -20 – During these 5 overs the batting side tries to accelerate the scoring rate, while the bowling side will try to restrict the batsmen against going for big hits

This is shown below

This latest update of GooglyPlusPlus2021 includes the following functions

a) Match tab

  1. teamRunsAcrossOvers
  2. teamSRAcrossOvers
  3. teamWicketsAcrossOvers
  4. teamERAcrossOvers
  5. matchWormWickets

b) Head-to-head tab

  1. teamRunsAcrossOversOppnAllMatches
  2. teamSRAcrossOversOppnAllMatches
  3. teamWicketsAcrossOversOppnAllMatches
  4. teamERAcrossOversOppnAllMatches
  5. topRunsBatsmenAcrossOversOppnAllMatches
  6. topSRBatsmenAcrossOversOppnAllMatches
  7. topWicketsBowlersAcrossOversOppnAllMatches
  8. topERBowlerAcrossOverOppnAllMatches

c) Overall performance tab

  1. teamRunsAcrossOversAllOppnAllMatches
  2. teamSRAcrossOversAllOppnAllMatches
  3. teamWicketsAcrossOversAllOppnAllMatches
  4. teamERAcrossOversAllOppnAllMatches
  5. topRunsBatsmenAcrossOversAllOppnAllMatches
  6. topSRBatsmenAcrossOversAllOppnAllMatches
  7. topWicketsBowlersAcrossOversAllOppnAllMatches
  8. topERBowlerAcrossOverAllOppnAllMatches

Hence a total of 8 + 8 + 5 = 21 functions have been added. These functions can be utilized across all the 9 T20 formats that are supported in GooglyPlusPlus2021 namely

i) IPL ii) Intl. T20 (men) iii) Intl. T20 (women) iv) BBL v) NTB vi) PSL vii) CPL viii) SSM ix) WBB

Hence there are a total of 21 x 9 = 189 new possibilities to explore in GooglyPlusPlus2021

GooglyPlusPlus2021 is based on my R package yorkr and is based on data from Cricsheet. To know how to use GooglyPlusPlus see any of earlier posts GooglyPlusPlus2021 is now fully interactive!!!, GooglyPlusPlus2021 adds new bells and whistles!!, GooglyPlusPlus2021 enhanced with drill-down batsman, bowler analytics

Take GooglyPlusPlus for a spin here GooglyPlusPlus2021-9

You can clone/fork the code for the Shiny app from Github – gpp2021-9

Included below is a random selection of options from the 189 possibilities mentioned above. Feel free to try out for yourself

A) IPL – CSK vs KKR 2018-04-10

a) Team Runs in power play, middle and death overs

b) Team Strike rate in power play, middle and death overs

B) Intl. T20 (men) – India vs Afghanistan (2021-11-03)

a) Team wickets in power play, middle and death overs

b) Team Economy rate in power play, middle and death overs

C) Intl. T20 (women) Head-to-head : India vs Australia since 2018

a) Team Runs in all matches in power play, middle and death overs

D) PSL Head-to-head strike rate since 2019

a) Team vs team Strike rate : Karachi Kings vs Lahore Qalanders since 2019 in power play, middle and death overs

E) Team overall performance in all matches against all opposition

a) BBL : Brisbane Heats : Team Wickets between 2015 – 2018 in power play, middle and death overs

F) Top Runs and Strike rate Batsman of Mumbai Indians vs Royal Challengers Bangalore since 2018

a) Top runs scorers for Mumbai Indians (MI) in power play, middle and death overs

b) Top strike rate for RCB in power play, middle and death overs

F) Intl. T20 (women) India vs England since 2018

a) Top wicket takers for England in power play, middle and death overs since 2018

b) Top wicket takers for India in power play, middle and death overs since 2018

G) Intl. T20 (men) All time best batsmen and bowlers for India

a) Most runs in power play, middle and death overs

b) Highest strike rate in power play, middle and death overs

H) Match worm wicket chart

In addition to the usual Match worm chart, I have also added a Match Wicket worm chart in the latest version

Note: You can zoom to the area where you would like to focus more

The option of looking at the Match worm chart (without wickets) also exists.

Go ahead take GooglyPlusPlus2021 for a test drive and check out how your favourite players perform in power play, middle and death overs. Click GooglyPlusPlus2021-9

You can fork/download the app code from Github at gpp2021-9

Hope you have fun with GooglyPlusPlus

You may also like

  1. Using Linear Programming (LP) for optimizing bowling change or batting lineup in T20 cricket
  2. Practical Machine Learning with R and Python – Part 6
  3. Big Data 6: The T20 Dance of Apache NiFi and yorkpy
  4. Understanding Neural Style Transfer with Tensorflow and Keras
  5. Using Reinforcement Learning to solve Gridworld
  6. Exploring Quantum Gate operations with QCSimulator
  7. Experiments with deblurring using OpenCV
  8. Deep Learning from first principles in Python, R and Octave – Part 5
  9. Re-introducing cricketr! : An R package to analyze performances of cricketers
  10. Natural language processing: What would Shakespeare say?

To see all posts click Index of posts

GooglyPlusPlus2021:ICC WC T20:Pavilion-view analytics as-it-happens!

This year 2021, we are witnessing a rare spectacle in the cricketing universe, where IPL playoffs are immediately followed by ICC World Cup T20. Cricket pundits have claimed such a phenomenon occurs once in 127 years! Jokes apart, the World cup T20 is underway and as usual GooglyPlusPlus is ready for the action.

GooglyPlusPlus will provide near-real time analytics, by automatically downloading the latest match data daily, processing and organising the match data into appropriate folders so that my R package yorkr can slice and dice the data to provide the pavilion-view analytics.

The charts capture all the breathless, heart-pounding, and nail-biting action in great details in the many tables and plots. Every table and chart tell a story. You just have to ‘read between the lines!’

GooglyPlusPlus2021 will update itself automatically every day, so the data will be current and you can analyse all matches upto the previous day, along with the historical performances of the teams. So make sure you check it everyday.

Note:

  1. All charts are interactive. To know how to use the interactive charts see my post GooglyPlusPlus2021 is now fully interactive!!!
  2. The are 5 tabs for each of the formats supported by GooglyPlusPlus2021 which now supports IPL, Intl. T20(men), Intl. T20(women), BBL, NTB, PSL, CPL, SSM, WBB. Besides, it also supports ODI (men) and ODI (women)
  3. Each of the formats have 5 tabs – Batsman, Bowler, Match, Head-to-head and Overall Performace.
  4. All T20 formats also include a ranking functionality for the batsmen and bowlers
  5. You can now perform drill-down analytics for batsmen, bowlers, head-to-head and overall performance based on date-range selector functionality. The ranking tabs also include date range selector granular analysis. For more details see GooglyPlusPlus2021 enhanced with drill-down batsman, bowler analytics

Try out GooglyPlusPlus2021 here gpp2021-8!!

You can clone fork the code from Github gpp2021-8

I am including some random screenshots of things that can be done with GooglyPlusPlus2021

A. Papua New Guinea vs Oman (2021-10-17)

a. Batting partnership

B. Match worm chart (New Papua Guinea v Oman)

This was a no contest as Oman cruised to victory

C. Scotland vs Bangladesh (2021-10-17)

a. Scorland upset Bangladesh

b. March worm chart (Scotland vs Bangladesh)

Fortunes see-sawed one way, then another, as can be seen in the match worm chart

C. Netherlands vs Ireland (2021-10-18)

a. Batman vs Bowler

D. Historical performance head-to-head

a. Sri Lanka vs West Indies (2019-2021) – Batting partnerships

b. India vs England (2018 – 2021) – Bowling scorecard

c) Australia vs South Africa – Team wicket opposition

E) Overall performance

a. Pakistan batting scorecard since 2019

a. Win loss of Australia since 2019

F) Batsman Performance

a. PR Stirling’s runs against opposition since 2019

b. KJ Brien’s cumulative average runs since 2019

G. Bowler performance

a. PWH De Silva’s wicket prediction since 2019

b. T Shamsi’s cumulative average wickets since 2019

H. Ranking Intl. T20 batsman since 2019

a. Runs over Strike rate

b. Strike rate over runs

I. Ranking bowlers since 2019

a. Wickets over Economy rate

b. Economy rate over wickets

As mentioned above GooglyPlusPlus2021 will be updated daily automatically, so you won’t miss any analytic action.

Do give GooglyPlusPlus2021 a spin!

Clone/fork the code for the Shiny app from Github gpp2021-8

You may also like

  1. Natural language processing: What would Shakespeare say?
  2. Literacy in India – A deepR dive
  3. Practical Machine Learning with R and Python – Part 5
  4. Big Data 7: yorkr waltzes with Apache NiFi
  5. Getting started with Tensorflow, Keras in Python and R
  6. Deep Learning from first principles in Python, R and Octave – Part 7
  7. Introducing QCSimulator: A 5-qubit quantum computing simulator in R
  8. Video presentation on Machine Learning, Data Science, NLP and Big Data – Part 1

To see all post click Index of posts

GooglyPlusPlus2021 enhanced with drill-down batsman, bowler analytics

This latest update to GooglyPlusPlus2021 includes the following changes

a) All the functions in the ‘Batsman’ and ‘Bowler ‘tabs now include a date range, which allows you specify a period of interest.

b) The ‘Rank Batsman’ and ‘Rank Bowler’ tabs also include a date range selector, against the earlier version which had a ‘Since year’ slider see GooglyPlusPlus2021 bubbles up top T20 players in all formats!. The earlier ‘Since year’ slider option could only rank for the latest year or for all years up to the current year. Now with the new ‘date range’ picker we can check the batsman and bowler ranks in any IPL season or (any T20 format) or for a range of years.

c) Note: The Head-to-head and Overall performance tabs already include a date range selector.

There are 10 batsman functions and 9 bowler function that have changed for the following T20 and ODI formats and Rank batsman and bowler includes the ‘date range’ and has changed for all T20 formats.

GooglyPlusPlus2021 supports all the following T20 formats

i) IPL ii) Intl T20(men) iii) Intl T20(women) iv) BBL v) NTB vi) PSL vii) WBB viii) CPL ix) SSM T20 formats – ( 9 T20 panels)

i) ODI (men) ii) ODI (women) – 2 ODI panels

i.e. the changes impact (10 + 9) x 11 + (1 + 1 ) x 9 = 227 tabs which have been changed

The addition of date range enables a fine-grained analysis of players as the players progress through the years.

Note: All charts are interactive. To see how to use interactive charts of GooglyPlusPlus2021 see

GooglyPlusPlus2021 is now fully interactive!!!

GooglyPlusPlus2021 is based on my R package yorkr. The data is take from Cricsheet

You can clone/fork this latest version of GooglyPlusPlus2021 from Github at gpp2021-7

Check out the Shiny app here GooglyPlusPlus2021!!!

I have included some random screen shots of some of using these tabs and options in GooglyPlusPlus2021.

A) KL Rahul’s Cumulative average in IPL 2021 vs IPL 2020

a) KL Rahul in IPL 2021

b) KL Rahul in IPL 2020

B) Performance of Babar Azam in Intl. T20 (men)

a) Babar Azam’s cumulative average from 2019

b) Babar Azam’s Runs against opposition since 2019

Note: Intl. T20 (women) data available upto Mar 2020 from Cricsheet

a) A J Healy performance between 2010 – 2015

b) A J Healy performance between 2015 – 2020

D) M S Dhoni’s performance with the bat pre-2020 and post 2020

There has been a significant decline in Dhoni’s performance in the last couple of years

I) Dhoni’s performance from Jan 2010 to Dec 2019

a) Moving average at 25+ (Dhoni before)

The moving average actually moves up…

b) Cumulative average at 25+ (Dhoni before)

c) Cumulative Strike rate 140+ (Dhoni before)

d) Dhoni’s moving average is ~10-12 (post 2020)

e) Dhoni’s cumulative average (post 2020)

f) Dhoni’s strike rate ~80 (post 2020)

E) Bumrah’s performance in IPL

a) Bumrah’s performance in IPL 2020

b) Bumrah’s performance in IPL 2021

F) Moving average wickets for A. Shrubsole in ODI (women)

G) Chris Jordan’s cumulative economy rate

We can see that Jordan has become more expensive over the years

G) Ranking players

In this latest version the ‘Since year slider’ has been replaced with a Date Range selector. With this we can identify the player ranks in any IPL, CPL, PSL or BBL season. We can also check the performance over the last couple of years. Note: The matches played and Runs over Strike rate or Strike rate over runs can be computed. Similarly for bowlers we have Wickets over Economy rate and Economy rate over wickets options.

a) Ranking IPL batsman in IPL season 2020

b) Ranking Intl. T20 (batsmen) from Jan 2019 to Jul 2021

c) Ranking Intl. T20 bowlers (women) from Jan 2019 – Jul 2021

d) Best IPL bowlers over the last 3 seasons (Wickets over Economy rate)

e) Best IPL bowlers over the last 3 seasons (Economy rate over wickets)

You can clone/download this latest version of GooglyPlusPlus2021 from Github at gpp2021-7

Take GooglyPlusPlus2021 for a spin!!

Hope you have fun checking out the different tabs with the different options!!

Also see

  1. Deconstructing Convolutional Neural Networks with Tensorflow and Keras
  2. Using Reinforcement Learning to solve Gridworld
  3. Introducing QCSimulator: A 5-qubit quantum computing simulator in R
  4. De-blurring revisited with Wiener filter using OpenCV
  5. Deep Learning from first principles in Python, R and Octave – Part 5
  6. Big Data-4: Webserver log analysis with RDDs, Pyspark, SparkR and SparklyR
  7. Practical Machine Learning with R and Python – Part 4
  8. Pitching yorkpy…on the middle and outside off-stump to IPL – Part 2
  9. What would Shakespeare say?
  10. Bull in a china shop – Behind the scenes in android

To see more posts click Index of posts

GooglyPlusPlus2021: Restarting IPL 2021 as-it-happens!!!

The IPL 2021 extravaganza has restarted again, now in Dubai, and it was time for me to crank up good ol’ GooglyPlusPlus2021. As in my earlier post, GooglyPlus2021 with IPL 2021 as it happens, during the initial set of IPL 2021 games,, a command script will execute automatically every day, download the latest data files, unzip, sort, process and put them in appropriate directories so that GooglyPlusPlus can work its magic on the data, with my R package yorkr. You can do analysis of IPL 2021 matches, batsmen, bowlers, historical performance analysis of head-to-head clashes and performances of teams.

Note: Since the earlier instalment of IPL 2021, there are 2 key changes that have taken place in GooglyPlusPlus.

Now,

a) All charts are interactive. You can hover over charts, click, double-click to get more details. To see more details on how to use the interactive charts, see my post GooglyPlusPlus2021 is now fully interactive!

b) You can now analyse historical performances, compute team batting and bowling scorecards for specified periods. To know details see GooglyPlusPlus2021 adds new bells and whistles!

You can try out my app GooglyPlusPlus2021 by clicking GooglyPlusPlus2021

The code for my R package yorkr is available at Github at yorkr

You can clone/fork GooglyPlusPlus2021 from github at gpp2021-6

IPL 2021 is already underway.

Some key analysis and highlights of the 2 recently concluded IPL matches

  • CSK vs MI
  • KKR vs RCB

a) CSK vs MI (19 Sep 2021) – Batting Partnerships (CSK)

b) CSK vs MI (19 Sep 2021) – Bowling scorecard (MI)

c) CSK vs MI (19 Sep 2021) – Match worm chart

Even though MI had a much better start and were cruising along to a victory, they lost the plot around the 18.1 th over as seen below (hover on the chart)

d

d) KKR vs RCB ( 20 Sep 2021) – Bowling wicket match

This chart gives the wickets taken by the bowler and the total runs conceded

e) KKR vs RCB ( 20 Sep 2021) – Match worm chart

This was a no contest. RCB batting was pathetic and KKR blasted their way to victory as seen in this worm chart

Note: You can also do historical analysis of teams with GooglyPlusPlus2021

For the match to occur today PBKS vs RR (21 Sep 2021) we can perform head-to-head historical analysis. Here Kings XI Punjab has been chosen instead of Punjab Kings as that was its name.

f) Head-to-head (PBKS vs RR) today’s match 21 Sep 2021

For the Rajasthan Royals Sanjy Samson and Jos Buttler have the best performance from 2018 -2021 as seen below

For Punjab Kings KL Rahul and Chris Gayle are the leading scorers for the period 2018-2021

g) Current ranking of batsmen IPL 2021

h) Current ranking of bowlers IPL 2021

Also you analyse individual batsman and bowlers

i) Batsman analysis

To see Rituraj Gaikwad performance checkout the batsman tab

j) Bowler analysis

Performance of Varun Chakaravarty

Remember to check out GooglyPlusPlus2021 for your daily analysis of matches, teams, batsmen and bowlers. Your ride will be waiting for you!!!

You can clone/fork GooglyPlusPlus2021 from github at gpp2021-6

GooglyPlusPlus2021 has been updated with all completed 31 matches

 

Mumbai Indians-Royal Challengers Bangalore-2021-04-09Chennai Super Kings-Delhi Capitals-2021-04-10
Kolkata Knight Riders-Sunrisers Hyderabad-2021-04-11Punjab Kings-Rajasthan Royals-2021-04-12
Mumbai Indians-Kolkata Knight Riders-2021-04-13Royal Challengers Bangalore-Sunrisers Hyderabad-2021-04-14
Delhi Capitals-Rajasthan Royals-2021-04-15Punjab Kings-Chennai Super Kings-2021-04-16
Mumbai Indians-Sunrisers Hyderabad-2021-04-17Royal Challengers Bangalore-Kolkata Knight Riders-2021-04-18
Punjab Kings-Delhi Capitals-2021-04-18Chennai Super Kings-Rajasthan Royals-2021-04-19
Mumbai Indians-Delhi Capitals-2021-04-20Punjab Kings-Sunrisers Hyderabad-2021-04-21
Chennai Super Kings-Kolkata Knight Riders-2021-04-21Rajasthan Royals-Royal Challengers Bangalore-2021-04-22
Mumbai Indians-Punjab Kings-2021-04-23Kolkata Knight Riders-Rajasthan Royals-2021-04-24
Chennai Super Kings-Royal Challengers Bangalore-2021-04-25Delhi Capitals-Sunrisers Hyderabad-2021-04-25
Punjab Kings-Kolkata Knight Riders-2021-04-26Royal Challengers Bangalore-Delhi Capitals-2021-04-27
Sunrisers Hyderabad-Chennai Super Kings-2021-04-28Rajasthan Royals-Mumbai Indians-2021-04-29
Kolkata Knight Riders-Delhi Capitals-2021-04-29Punjab Kings-Royal Challengers Bangalore-2021-04-30.RData
Chennai Super Kings-Mumbai Indians-2021-05-01Rajasthan Royals-Sunrisers Hyderabad-2021-05-02
Punjab Kings-Delhi Capitals-2021-05-02Chennai Super Kings-Mumbai Indians-2021-09-19
Royal Challengers Bangalore-Kolkata Knight Riders-2021-09-20Rajasthan Royals-Punjab Kings-2021-09-21
Sunrisers Hyderabad-Delhi Capitals-2021-09-22.RDataMumbai Indians-Kolkata Knight Riders-2021-09-23.RData
Royal Challengers Bangalore-Chennai Super Kings-2021-09-24.RDataPunjab Kings-Sunrisers Hyderabad-2021-09-25
Delhi Capitals-Rajasthan Royals-2021-09-25.RDataRoyal Challengers Bangalore-Mumbai Indians-2021-09-26.RData
Kolkata Knight Riders-Chennai Super Kings-2021-09-26.RDataKolkata Knight Riders-Chennai Super Kings-2021-09-26.RData
Delhi Capitals-Kolkata Knight Riders-2021-09-28.RDataRajasthan Royals-Royal Challengers Bangalore-2021-09-29.RData
Sunrisers Hyderabad-Chennai Super Kings-2021-09-30.RDataKolkata Knight Riders-Punjab Kings-2021-10-01.RData
Chennai Super Kings-Rajasthan Royals-2021-10-02.RDataMumbai Indians-Delhi Capitals-2021-10-02.RData
Royal Challengers Bangalore-Punjab Kings-2021-10-03.RDataChennai Super Kings-Delhi Capitals-2021-10-04.RData
Rajasthan Royals-Mumbai Indians-2021-10-05.RDataSunrisers Hyderabad-Royal Challengers Bangalore-2021-10-06.RData

Also see

  1. Deep Learning from first principles in Python, R and Octave – Part 5
  2. Introducing QCSimulator: A 5-qubit quantum computing simulator in R
  3. Computer Vision: Ramblings on derivatives, histograms and contours
  4. Designing a Social Web Portal
  5. Understanding Neural Style Transfer with Tensorflow and Keras
  6. Big Data 6: The T20 Dance of Apache NiFi and yorkpy
  7. Practical Machine Learning with R and Python – Part 6
  8. Introducing cricpy:A python package to analyze performances of cricketers
  9. A closer look at “Robot Horse on a Trot” in Android
  10. Cricketr adds team analytics to its repertoire!!!

To see all posts click Index of posts

GooglyPlusPlus2021 bubbles up top T20 players in all formats!

“Would you tell me, please, which way I ought to go from here?”
“That depends a good deal on where you want to get to.”
“I don’t much care where –”
“Then it doesn’t matter which way you go.”
                              Lewis Carroll, Alice in Wonderland

This latest version of GooglyPlusPlus2021 has the following updates

– brand new strategy and algorithm for ranking T20 players in any format (IPL, BBL, NTB, PSL etc.)

– integrates the Caribbean Premier League T20 into the app

– includes the latest BBL matches in 2020-2021

– includes all the latest Natwest T20 matches 2020

– has a new and better user interface

Interestingly the new Ranking algorithm has come just before the IPL auction. Check out who’s who in IPL T20 by taking GooglyPlusPlus2021 for ride!!!

Try out GooglyPlusPlus2021!!

You can clone/fork the code from Github at GooglyPlusPlus2021

1) Ranking Algorithm

In my last post GooglyPlusPlus2021 interactively ranks T20 batsmen and bowlers!!!  I had shown how by changing the number of matches played we see that KL Rahul and Rishabh Pant move above Virat Kohli. That set me thinking. So, I redesigned the ranking so that we start to identify newer players earlier.  This is how the new ranking works.

a) Ranking T20 batsmen :

I have the following controls

a) Since year : This tells the year range  to consider for the  batsmen. This slider moves from right to left

b) Matches played : Number of matches played by the batsman in the year range. This moves left to right

c) Mode : The ranking algorithm sorts on and ranks on 2 columns namely Runs and Strike rate. The mode tells whether to consider Runs over Strike rate of Strike rate over runs. 

By default, the control for “Since year” will be set to the ‘beginning of time’ which for IPL data is 2008. If you move the ‘Since year’ since year slider to the left, the ‘Matches played’ slider will move to the right and the corresponding maximum value of matches played will be set appropriately.

b) Ranking T20 Bowlers:

This has the following controls

a) Since year : This tells the year range to consider for  bowler in IPL. Moves right to left.

b) Matches played : Number of matches played by the bowler in the year range. Move left to right.

c) Mode 1: The bowlers are sorted and ranked on 2 columns namely Wickets and Economy rate. The mode tells whether to consider Wickets over Economy rate or Economy rate over wickets when ranking the bowlers. 

By default, the “Since year” will be set to the year when the T20 data is available. If you move the ‘Since year’ since year slider to the left, the ‘Matches played’ slider will move to the right and the corresponding maximum value of matches played will be set appropriately.

2) Strategy for ranking:

Here is the rationale and philosophy behind these controls

The ranking in my earlier post GooglyPlusPlus2021 interactively ranks T20 batsmen and bowlers!!!  is based on sorting batsmen and bowlers from the start of IPL tournament. Hence we will find players who have played a lot of matches. So in the bowler ranking you will SL Malinga who no longer plays IPL.

Hence I decided that the user should be allowed to choose the start year to consider for the ranking. We can move the “Since year’ slider from right to left to choose the data for the year range we are interested in e.g. (2014-2020, or 2017-2020). Changing the ‘Since year’ slider will obviously change the maximum matches played by any player. However the user can move this slider right to left and decide the number of matches to be considered for a batsman or bowler.  Finally, the ‘Mode’. will allow the user to choose whether the list if batsmen should be ranked first by average runs and then average strike rate or vice versa. In the case of bowlers, the choice is whether to first sort by number of wickets and then economy rate or vice versa. 

The consideration for ‘Mode’ and “Mode1′ is that while runs and wickets are important for batsman or bowler, it is clear the Strike rate and Economy rate become critical in ‘death overs‘. Batsmen who can accelerate the scoring rate when needed and bowlers who can put the brakes on during death overs is of paramount importance in T20 cricket.

Let me walk through a  few scenarios in IPL T20. The same functionality is also available in alll other T20 formats (Intl. T20 (men, women), BBL, NTB, PSL, WBB, CPL etc.)

3) Ranking IPL batsmen

Note: Those players who are underlined in red are the shooting stars**

a) Scenario 1

These are  the consistent and reliable players

Since year = 2013, Matches played = 95 and Mode = ‘Runs over Strike Rate’

 

 

b) Scenario 2

Since year = 2015, Matches played = 67 and Mode = ‘Runs over Strike Rate’

c) Scenario 3

We can turn the above over its head and choose Mode = “Strike rate over Runs’

Since year = 2015, Matches played = 67 and Mode = ‘Strike Rate over Runs’

d) Scenario 4: 

Since year = 2018, Matches played = 35 and Mode = ‘Runs over Strike Rate’

4) Ranking IPL bowlers

e) Scenario 5:

Since year = 2016, Matches played = 55 and Mode1 = ‘ Wickets over Economy Rate’

f) Scenario 6

Since year = 2018, Matches played = 33 and Mode1 = ‘ Economy Rate over wickets’. Note the economy rate is sorted in ascending order

Note:  Incidentally the ranking of IPL and other T20 players in my earlier posts is a special case, when you consider all matches from the beginning of time (or since the data is available, rather than choosing a range from later years).

Note 1: Personally, if I had to form a team, I would choose

– at least 2-3 batsmen who are reliable and have good average runs and a good strike rate

– 2 batsmen who can be used to accelerate strike rate during critical junctures or at death overs

– 2-3 bowlers who have a great record of wicket taking with good economy rate (2 + 1 pace/spin)

– 2 bowlers who have good economy rate over wickets

– 2 all rounders with good batting and bowling average

– 1 wicketkeeper batsmen

The key point is how many matches would you consider as a minimum for reliability or strike rate. More is good but not always better as you could miss out on rising stars* who may be risky but good picks and possibly cost less, since the team composition will also depend on the available budget for each team. You could also check other T20 formats for good T20 players. Creating a T20 team in IPL is an optimization problem where the objective is to maximize the runs, strike rate for batsmen,  or maximizing the wickets taken, while minimizing the economy rate for bowlers with the constraint of the overall budget of the team.

Note 2: The ranking algorithm has been included for all T20 formats in GooglyPlusPlus2020. See below

5) International T20 Batsmen (men) ranking

Since year = 2012, Matches played = 50 and Mode = ‘Runs over Strike Rate’

 

6) International T20 Bowlers (men) ranking

Since year = 2013, Matches played = 33 and Mode1 = ‘Wickets over Economy Rate ‘

Here are some top class T20 bowlers

 

7) International T20 Batsmen (women) ranking

Since year = 2015, Matches played = 29 and Mode = ‘Runs over Strike Rate’. Smriti Mandhana makes it to the top 3 in Runs over Strike Rate!

 

 

and 2nd when Strike rate over runs is considered!

 

8) Integrating Carribean Premier League T20

In this version I have also integrated Carribean Premier League (CPL). It took me about 3 -4  hours of focused work to setup the data and the associated code. Like every other T20 format,  CPL league has access to 100+ functions of yorkr. So you can do analysis of CPL batsmen, bowlers, CPL matches, CPL head-to-head confrontation and CPL team against all other teams besides the ranking function. You can also generate batting and bowling scorecard for matches, for a team against all other teams and the overall scorecard in all matches against all other teams. Here is a random sample

a) C Munro – Cumulative Average Runs

 

b) RR Emrit – Bowler’s wickets against opposition

 

c) Head-to-head (Barbados Tridents vs Antigua Hawkbill all matches)

 

d) Rank CPL batsmen 

Since year= 2016, Matches played = 41 Mode = Strike rate over Runs

Nicholas Pooran tops the list

9) BBL 2020-21

GooglyPlusPlus2021 now has the latest Big Bash League matches of 2020-21, in fact “hot off the pitch“. So you should be able to do all the analysis on current BBL data namely batsmen and bowler analysis, match analysis, team analysis vs another team or against all other teams, and finally ranking of batsmen and bowlers. Here is a sample with yesterday’s match

a) Match scorecard -Perth Scorchers- Sydney Sixers 06 Feb 2021 (Final)

 

b) Predict runs of batsman – CA Lynn

 

10) Natwest T20 Blast 2020

I noticed recently the Cricsheet  has more data. Now NTB data includes all matches till 2020. This data has been incorporated into NTB and you should be able to use all the yorkr functions to analyze batsmen, bowlers, teams, team-vs-team and team vs all other teams, besides the ranking functions. Here are a couple below

a) Head-to-head Derbyshire vs Essex all matches

 

b) Team Batsmen vs Bowlers – All matches all opposition Leicestershire (MJ Cosgrove)

 

Do check out the various functions of GooglyPlusPlus2021. Take a look at the ranks of the T20 batsmen and bowlers. Hope you have a good time!

Take GooglyPlusPlus2021 for a test ride!!

Feel free to clone/fork the code from Github at GooglyPlusPlus2021

Also see

  1. Cricketr adds team analytics to its repertoire!!!
  2. Introducing cricket package yorkr: Part 2-Trapped leg before wicket
  3. Introducing cricpy:A python package to analyze performances of cricketers
  4. Big Data-5: kNiFi-ing through cricket data with yorkpy
  5. Using Linear Programming (LP) for optimizing bowling change or batting lineup in T20 cricket
  6. See all 72+ posts on cricket in R, Python and Octave
  7. Deep Learning from first principles in Python, R and Octave – Part 5
  8. Practical Machine Learning with R and Python – Part 3
  9. Understanding Neural Style Transfer with Tensorflow and Keras

To see all post click Index of posts

 

 

GooglyPlusPlus2021 interactively ranks T20 batsmen and bowlers!!!

Every time I think that I have my R packages or Shiny apps all wrapped up, I find another idea trots up and knocks at my door. Since I intend to keep GooglyPlusPlus current with the latest data, I decided to include the ranking functions in my Shiny app GooglyPlusPlus.

Fortunately, since GooglyPlusPlus is based on my R package ‘yorkr‘ (see Introducing cricket package yorkr: Beaten by sheer pace!), I could make the necessary changes to the ranking functions in the package, so that it could be incorporated into my latest Shiny app GooglyPlusPlus2021!! To know how to use GooglyPlusPlus see my post Introducing GooglyPlusPlus

Note: GooglyPlusPlus can analyze batsmen, bowlers, matches and teams.

Take GooglyPlusPlus2021 for a test drive!!!

You can clone/fork GooglyPlusPlus2021 from Github

Here are a few scenarios from GooglyPlusPlus2021

A) Ranking batsmen

Ranking IPL batsmen (minMatches = 80) – The following table shows the ranking of IPL players who have played 80 matches or more

B) Identifying batsmen of potential and promise

Ranking IPL batsmen (minMatches =70) –  If we reduce the minimum number of matches played to 70, then we see it pushes up KL Rahul above Kohli.

Ranking IPL batsmen (minMatches =60) – When the slider is moved to 60, we see that Rishabh Pant has a better mean average and mean strike rate and is also ranked above Kohli. We can identify promising players this way. However, it is also likely that some players may be just a bright flash in the pan

C) Ranking T20 bowlers (men)

D) Ranking NTB Batsmen

GooglyPlusPlus2021 can rank all T20 formats (IPL, BBL, Intl. T20 (men), Intl. T20 (women), NTB, PSL and WBB. Do give it a try!

Also remember that GooglyPlusPlus2021 includes close to 100+ functions which enable it to perform analysis of batsmen, bowlers, T20 matches, head-to-head confrontation of T20 teams and overall performance of T20 teams . To know more about GooglyPlusPlus2021 see Introducing GooglyPlusPlus

You can download the code for this app from Github at GooglyPlusPlus2021

Do give GooglyPlusPlus2021 a spin!!

I do have some other ideas also which I will be incorporating  into GooglyPlusPlus2021.

Watch this space!!

Also see
1. Deep Learning from first principles in Python, R and Octave – Part 7
2. A method to crowd source pothole marking on (Indian) roads
3. Big Data 7: yorkr waltzes with Apache NiFi
4. Understanding Neural Style Transfer with Tensorflow and Keras
5. Revisiting World Bank data analysis with WDI and gVisMotionChart
6. Natural language processing: What would Shakespeare say?
7. Introducing QCSimulator: A 5-qubit quantum computing simulator in R
8. Introducing cricpy:A python package to analyze performances of cricketers
9. Simulating an Edge Shape in Android

To see all posts click Index of posts

Introducing GooglyPlusPlus!!!

“We can lift ourselves out of ignorance, we can find ourselves as creatures of excellence and intelligence and skill.”
“Heaven is not a place, and it is not a time. Heaven is being perfect.”
“Your whole body, from wingtip to wingtip, is nothing more than your thought itself, in a form you can see. Break the chains of your thought, and you break the chains of your body, too.”

From Jonathan Livingstone Seagull, by Richard Bach

Introduction

The metamorphosis is complete, from eggs to the butterfly! My R package yorkr, went on to become Googly,  and then to GooglyPlus and  now finally GooglyPlusPlus. My latest R Shiny app now provides interactive visualisation of almost all data in Cricsheet. GooglyPlusPlus visualizes the following matches

1. ODI (men)
2. ODI (women)
3. Intl. T20 (men)
4. Intl T20 (women)
5. IPL (Indian Premier League)
6. BBL (Big Bash League)
7. NTB (Natwest T20)
8. PSL (Pakistan Super League)
9. WBBL – Women’s BBL

GooglyPlusPlus is entirely based on my R package yorkr. To know more about yorkr see ‘Revitalizing R package yorkr‘ and the roughly 25+ posts on yorkr in Index of posts

This Shiny app was quite involved, and it took a lot of work to keep things organised and separate for the different forms of cricket. Anyway it is done and I am happy with the outcome.

Before you use the app, I would suggest that you take a look at the video “How to use GooglyPlusPlus?“. In this video, I show the different features of GooglyPlusPlus and how to navigate through them.

Check out GooglyPlusPlus Shiny at GooglyPlusPlus

You can clone/fork and play around with the code of GooglyPlusPlus here at Github

A. Highlights of GooglyPlusPlus.

The R Shiny app GooglyPlusPlus has the following main pages for the 9 different cricket formats. See below

 

Important note: Below I will be including some random output from the GooglyPlusPlus app for different match formats, however there is a lot more features in GooglyPlusPlus

1.  Indian Premier League (IPL)

a. IPL batsman – Batsman Runs vs Deliveries

 

b. IPL Match – Match  batting scorecard

 

c. Head-to-head between 2 IPL Teams – Team Batsmen Batting Partnership All Matches

 

 

 

d. Overall Performance – Team Bowling Scorecard Overall

 

 

 

2. International T20 Men

a. Batsman Function- Runs vs Strike rate

 

 

 

b. Bowler Function – Mean Economy Rate

 

 

3. International T20 (Women)

a.Batsman Functions – Batsman Cumulative Average Runs

 

 

b. Intl T20 Women’s match – Match worm Graph

 

 

 

 

 

4. Big Bash League (BBL)

a.Head-to-Head: Team batsmen batting partnerships

 

b.  Overall Performance – Team batsmen vs bowlers

 

 

5. Natwest T20 (NTB)

a. Head-to-head : Team bowlers vs batsmen

 

 

 

b. Batsman Runs vs Deliveries

 

 

6. Pakistan Super League (PSL)

a. Overall Performance – Batsmen Partnership

 

b. Bowling Scorecard

 

7. Women’s Big Bash League (WBBL)

a. Bowler wicket against opposition

 

 

8. One Day International (ODI) Men

a. Batsman Runs Against Opposition

 

b. Team Batsmen against bowlers

 

 

9. One Day International (ODI) women)

a. Match Batting Scorecard

b. Batsman Cumulative Strike Rate

 

 

 

Conclusion

There you have it. I have randomly shown  2 functions for each cricket format. There are many functions in each tab for the for the different match formats – namely IPL, BBL, Intl T20 (men,women), PSL etc.  Go ahead and give GooglyPlusPlus a spin!

To try out GooglyPlusPlus click GooglyPlusPlus. Don’t forget to check out the video How to use GooglyPlusPlus?

You can clone/fork the code from Github at GooglyPlusPlus

Hope you have fun with GooglyPlusPlus!!

You may also like

1. Big Data 6: The T20 Dance of Apache NiFi and yorkpy
2. Deep Learning from first principles in Python, R and Octave – Part 7
3. De-blurring revisited with Wiener filter using OpenCV
4. Exploring Quantum Gate operations with QCSimulator
5. Latency, throughput implications for the Cloud
6. Programming Zen and now – Some essential tips-2
7. The Anomaly
8. Practical Machine Learning with R and Python – Part 3
9. Introducing cricpy:A python package to analyze performances of cricketers
10. The making of Total Control Android game

To see all posts click Index of posts