Data
Moneyball

Moneyball

active ARFF Publicly available Visibility: public Uploaded 28-01-2018 by Joaquin Vanschoren
0 likes downloaded by 0 people , 0 total downloads 0 issues 0 downvotes
  • Analytics Economics sport Sports study_130 study_93
Issue #Downvotes for this reason By


Loading wiki
Help us complete this description Edit
Author: MITx Source: [Kaggle](https://www.kaggle.com/wduckett/moneyball-mlb-stats-19622012/data), originally from [The Analytics Edge course on EdX](https://www.edx.org/course/analytics-edge-mitx-15-071x-3). Data collected from [baseball-reference.com](baseball-reference.com) Please cite: Moneyball In the early 2000s, Billy Beane and Paul DePodesta worked for the Oakland Athletics. While there, they literally changed the game of baseball. They didn't do it using a bat or glove, and they certainly didn't do it by throwing money at the issue; in fact, money was the issue. They didn't have enough of it, but they were still expected to keep up with teams that had much deeper pockets. This is where Statistics came riding down the hillside on a white horse to save the day. This data set contains some of the information that was available to Beane and DePodesta in the early 2000s, and it can be used to better understand their methods. ### Attributes This data set contains a set of variables that Beane and DePodesta focused heavily on. They determined that stats like on-base percentage (OBP) and slugging percentage (SLG) were very important when it came to scoring runs, however they were largely undervalued by most scouts at the time. This translated to a gold mine for Beane and DePodesta. Since these players weren't being looked at by other teams, they could recruit these players on a small budget. The variables are as follows: Team League Year Runs Scored (RS) Runs Allowed (RA) Wins (W) On-Base Percentage (OBP) Slugging Percentage (SLG) Batting Average (BA) Playoffs (binary) RankSeason RankPlayoffs Games Played (G) Opponent On-Base Percentage (OOBP) Opponent Slugging Percentage (OSLG) ### Acknowledgements This data set is referenced in The Analytics Edge course on EdX during the lecture regarding the story of Moneyball. The data itself is gathered from baseball-reference.com. Sports-reference.com is one of the most comprehensive sports statistics resource available, and I highly recommend checking it out. Inspiration It is such an important skill in today's world to be able to see the "truth" in a data set. That is what DePodesta was able to do with this data, and it unsettled the entire system of baseball recruitment. Beane and DePodesta defined their season goal as making it to playoffs. With that in mind, consider these questions: How does a team make the playoffs? How does a team win more games? How does a team score more runs? They are all simple questions with simple answers, but now it is time to use the data to find the "truth" hidden in the numbers.

15 features

RS (target)numeric374 unique values
0 missing
Teamnominal39 unique values
0 missing
Leaguenominal2 unique values
0 missing
Yearnumeric47 unique values
0 missing
RAnumeric381 unique values
0 missing
Wnumeric63 unique values
0 missing
OBPnumeric87 unique values
0 missing
SLGnumeric162 unique values
0 missing
BAnumeric75 unique values
0 missing
Playoffsnominal2 unique values
0 missing
RankSeasonnominal8 unique values
988 missing
RankPlayoffsnominal5 unique values
988 missing
Gnominal8 unique values
0 missing
OOBPnumeric72 unique values
812 missing
OSLGnumeric112 unique values
812 missing

62 properties

1232
Number of instances (rows) of the dataset.
15
Number of attributes (columns) of the dataset.
0
Number of distinct values of the target attribute (if it is nominal).
3600
Number of missing values in the dataset.
1118
Number of instances with at least one value missing.
9
Number of numeric attributes.
6
Number of nominal attributes.
-0.26
Mean kurtosis among attributes of the numeric type.
2
Number of binary attributes.
First quartile of mutual information between the nominal attributes and the target attribute.
389.08
Mean of means among attributes of the numeric type.
-0.13
First quartile of skewness among attributes of the numeric type.
Average mutual information between the nominal attributes and the target attribute.
0.02
First quartile of standard deviation of attributes of the numeric type.
-83.84
Average class difference between consecutive instances.
An estimate of the amount of irrelevant information in the attributes regarding the class. Equals (MeanAttributeEntropy - MeanMutualInformation) divided by MeanMutualInformation.
Second quartile (Median) of entropy among attributes.
Entropy of the target attribute values.
10.67
Average number of distinct values among the attributes of the nominal type.
-0.19
Second quartile (Median) of kurtosis among attributes of the numeric type.
0.01
Number of attributes divided by the number of instances.
0.05
Mean skewness among attributes of the numeric type.
0.42
Second quartile (Median) of means among attributes of the numeric type.
Number of attributes needed to optimally describe the class (under the assumption of independence among attributes). Equals ClassEntropy divided by MeanMutualInformation.
23.44
Mean standard deviation of attributes of the numeric type.
Second quartile (Median) of mutual information between the nominal attributes and the target attribute.
Percentage of instances belonging to the most frequent class.
Minimal entropy among attributes.
0.05
Second quartile (Median) of skewness among attributes of the numeric type.
Number of instances belonging to the most frequent class.
Maximum entropy among attributes.
-1.2
Minimum kurtosis among attributes of the numeric type.
13.33
Percentage of binary attributes.
0.03
Second quartile (Median) of standard deviation of attributes of the numeric type.
0.07
Maximum kurtosis among attributes of the numeric type.
0.26
Minimum of means among attributes of the numeric type.
90.75
Percentage of instances having missing values.
Third quartile of entropy among attributes.
1988.96
Maximum of means among attributes of the numeric type.
Minimal mutual information between the nominal attributes and the target attribute.
19.48
Percentage of missing values.
-0
Third quartile of kurtosis among attributes of the numeric type.
Maximum mutual information between the nominal attributes and the target attribute.
2
The minimal number of distinct values among attributes of the nominal type.
60
Percentage of numeric attributes.
715.08
Third quartile of means among attributes of the numeric type.
39
The maximum number of distinct values among attributes of the nominal type.
-0.18
Minimum skewness among attributes of the numeric type.
40
Percentage of nominal attributes.
Third quartile of mutual information between the nominal attributes and the target attribute.
0.3
Maximum skewness among attributes of the numeric type.
0.01
Minimum standard deviation of attributes of the numeric type.
First quartile of entropy among attributes.
0.19
Third quartile of skewness among attributes of the numeric type.
93.08
Maximum standard deviation of attributes of the numeric type.
Percentage of instances belonging to the least frequent class.
-0.33
First quartile of kurtosis among attributes of the numeric type.
53.18
Third quartile of standard deviation of attributes of the numeric type.
Average entropy of the attributes.
Number of instances belonging to the least frequent class.
0.33
First quartile of means among attributes of the numeric type.
14.14
Standard deviation of the number of distinct values among attributes of the nominal type.

13 tasks

3 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: root_mean_squared_error - target_feature: RS
0 runs - estimation_procedure: 10-fold Crossvalidation - evaluation_measure: predictive_accuracy - target_feature: RS
0 runs - estimation_procedure: 33% Holdout set - target_feature: RS
0 runs - estimation_procedure: 10-fold Crossvalidation - target_feature: RS
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
0 runs - estimation_procedure: 50 times Clustering
Define a new task