{ "metadata": { "name": "", "signature": "sha256:da0587c4279a82b4f3190d4c1933f8c30953bfad093f90abd12a897fa28388ec" }, "nbformat": 3, "nbformat_minor": 0, "worksheets": [ { "cells": [ { "cell_type": "markdown", "metadata": {}, "source": [ "## Pitches and Pitchers" ] }, { "cell_type": "code", "collapsed": false, "input": [ "import numpy as np\n", "import pandas as pd\n", "%matplotlib inline\n", "from ggplot import *" ], "language": "python", "metadata": {}, "outputs": [], "prompt_number": 1 }, { "cell_type": "code", "collapsed": false, "input": [ "# Inspect data, the data is pitches tracked over a 2 month stretch in the 2013\n", "# MLB season.\n", "baseball = pd.read_csv('./data/baseball-pitches-clean.csv')\n", "print baseball.shape[0], \" pitches were tracked.\"\n", "baseball.head()" ], "language": "python", "metadata": {}, "outputs": [ { "output_type": "stream", "stream": "stdout", "text": [ "133601 pitches were tracked.\n" ] }, { "html": [ "
\n", " | pitch_time | \n", "inning | \n", "top_or_bottom | \n", "pitcher_name | \n", "hitter_name | \n", "pitch_type | \n", "x | \n", "y | \n", "start_speed | \n", "end_speed | \n", "sz_top | \n", "sz_bottom | \n", "pfx_x | \n", "pfx_z | \n", "px | \n", "pz | \n", "x0 | \n", "y0 | \n", "ax | \n", "ay | \n", "\n", " |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "2013-10-01 20:07:43 -0400 | \n", "1 | \n", "Top | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "B | \n", "78.97 | \n", "164.92 | \n", "93.2 | \n", "85.3 | \n", "3.10 | \n", "1.53 | \n", "11.01 | \n", "6.47 | \n", "0.628 | \n", "1.547 | \n", "1.757 | \n", "50 | \n", "5.472 | \n", "-6.862 | \n", "... | \n", "
1 | \n", "2013-10-01 20:07:57 -0400 | \n", "1 | \n", "Top | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "S | \n", "82.40 | \n", "131.24 | \n", "93.4 | \n", "85.6 | \n", "3.06 | \n", "1.56 | \n", "10.14 | \n", "7.99 | \n", "0.545 | \n", "3.069 | \n", "1.711 | \n", "50 | \n", "5.650 | \n", "-6.693 | \n", "... | \n", "
2 | \n", "2013-10-01 20:08:12 -0400 | \n", "1 | \n", "Top | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "S | \n", "96.14 | \n", "161.47 | \n", "89.1 | \n", "82.8 | \n", "3.25 | \n", "1.53 | \n", "3.11 | \n", "4.95 | \n", "0.120 | \n", "1.826 | \n", "1.559 | \n", "50 | \n", "5.792 | \n", "-4.763 | \n", "... | \n", "
3 | \n", "2013-10-01 20:08:31 -0400 | \n", "1 | \n", "Top | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "S | \n", "106.44 | \n", "163.19 | \n", "90.0 | \n", "83.3 | \n", "3.25 | \n", "1.53 | \n", "-0.38 | \n", "2.15 | \n", "-0.229 | \n", "1.667 | \n", "1.172 | \n", "50 | \n", "5.832 | \n", "-3.519 | \n", "... | \n", "
4 | \n", "2013-10-01 20:09:09 -0400 | \n", "1 | \n", "Top | \n", "Francisco Liriano | \n", "Ryan Ludwick | \n", "B | \n", "163.95 | \n", "194.28 | \n", "87.7 | \n", "81.6 | \n", "3.62 | \n", "1.78 | \n", "1.62 | \n", "1.93 | \n", "-1.917 | \n", "0.438 | \n", "0.194 | \n", "50 | \n", "5.578 | \n", "-5.886 | \n", "... | \n", "
5 rows \u00d7 36 columns
\n", "\n", " | start_speed | \n", "end_speed | \n", "
---|---|---|
count | \n", "133601.000000 | \n", "133601.000000 | \n", "
mean | \n", "88.010358 | \n", "81.342203 | \n", "
std | \n", "5.959400 | \n", "5.320716 | \n", "
min | \n", "49.400000 | \n", "45.500000 | \n", "
25% | \n", "83.900000 | \n", "77.900000 | \n", "
50% | \n", "89.500000 | \n", "82.600000 | \n", "
75% | \n", "92.600000 | \n", "85.300000 | \n", "
max | \n", "103.400000 | \n", "95.500000 | \n", "
8 rows \u00d7 2 columns
\n", "\n", " | pitch_time | \n", "inning | \n", "pitcher_name | \n", "hitter_name | \n", "pitch_type | \n", "px | \n", "pz | \n", "pitch_name | \n", "start_speed | \n", "end_speed | \n", "type_confidence | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|
0 | \n", "2013-10-01 20:07:43 -0400 | \n", "1 | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "B | \n", "0.628 | \n", "1.547 | \n", "Fastball | \n", "93.2 | \n", "85.3 | \n", "0.894 | \n", "
1 | \n", "2013-10-01 20:07:57 -0400 | \n", "1 | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "S | \n", "0.545 | \n", "3.069 | \n", "Fastball | \n", "93.4 | \n", "85.6 | \n", "0.895 | \n", "
2 | \n", "2013-10-01 20:08:12 -0400 | \n", "1 | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "S | \n", "0.120 | \n", "1.826 | \n", "Slider | \n", "89.1 | \n", "82.8 | \n", "0.931 | \n", "
3 | \n", "2013-10-01 20:08:31 -0400 | \n", "1 | \n", "Francisco Liriano | \n", "Shin-Soo Choo | \n", "S | \n", "-0.229 | \n", "1.667 | \n", "Slider | \n", "90.0 | \n", "83.3 | \n", "0.926 | \n", "
4 | \n", "2013-10-01 20:09:09 -0400 | \n", "1 | \n", "Francisco Liriano | \n", "Ryan Ludwick | \n", "B | \n", "-1.917 | \n", "0.438 | \n", "Slider | \n", "87.7 | \n", "81.6 | \n", "0.915 | \n", "
5 rows \u00d7 11 columns
\n", "\n", " | pitch_time | \n", "inning | \n", "pitcher_name | \n", "hitter_name | \n", "pitch_type | \n", "px | \n", "pz | \n", "pitch_name | \n", "start_speed | \n", "end_speed | \n", "type_confidence | \n", "
---|---|---|---|---|---|---|---|---|---|---|---|
871 | \n", "2013-09-29 13:16:29 -0400 | \n", "1 | \n", "Justin Verlander | \n", "Juan Pierre | \n", "B | \n", "-1.422 | \n", "2.909 | \n", "Fastball | \n", "91.8 | \n", "83.5 | \n", "2 | \n", "
872 | \n", "2013-09-29 13:16:43 -0400 | \n", "1 | \n", "Justin Verlander | \n", "Juan Pierre | \n", "S | \n", "-0.868 | \n", "2.379 | \n", "Fastball | \n", "91.0 | \n", "83.1 | \n", "2 | \n", "
873 | \n", "2013-09-29 13:17:06 -0400 | \n", "1 | \n", "Justin Verlander | \n", "Juan Pierre | \n", "X | \n", "0.033 | \n", "1.891 | \n", "Fastball | \n", "91.5 | \n", "82.8 | \n", "2 | \n", "
874 | \n", "2013-09-29 13:17:51 -0400 | \n", "1 | \n", "Justin Verlander | \n", "Ed Lucas | \n", "S | \n", "0.670 | \n", "3.067 | \n", "Fastball | \n", "91.0 | \n", "82.9 | \n", "2 | \n", "
875 | \n", "2013-09-29 13:18:06 -0400 | \n", "1 | \n", "Justin Verlander | \n", "Ed Lucas | \n", "S | \n", "0.702 | \n", "1.819 | \n", "Fastball | \n", "90.6 | \n", "82.9 | \n", "2 | \n", "
5 rows \u00d7 11 columns
\n", "