import numpy as np
import pandas as pd
%matplotlib inline
from ggplot import *

# Inspect data, the data is pitches tracked over a 2 month stretch in the 2013
# MLB season.
baseball = pd.read_csv('./data/baseball-pitches-clean.csv')
print baseball.shape[0], " pitches were tracked."
baseball.head()

baseball.columns

# How many pitches types are there?
baseball.pitch_type.unique()

baseball.pitch_name.unique()

# How many pitchers are in the dataset?
len(baseball.pitcher_name.unique())

baseball.describe()[['start_speed', 'end_speed']]

slowest_pitch = baseball[baseball['start_speed'] == baseball['start_speed'].min(0)]
slowest_pitch.pitcher_name

zach_wheeler = baseball[baseball['pitcher_name'] == 'Zack Wheeler']
less_than_70 = zach_wheeler[zach_wheeler['start_speed'] < 70]
print 'Number of pitches under 70 mph =', len(less_than_70)
print 'Mean of Zach Wheeler\'s pitch speeds', round(zach_wheeler['start_speed'].mean(),2), 'MPH.'

print len(baseball[baseball['start_speed'] < 60]), 'pitches are under 60 mph'

# R.A. Dickey is a knuckleballer, one of only ones in the entire league
dickey = baseball[baseball['pitcher_name'] == 'R.A. Dickey']
print 'R. A. Dickey has ', len(dickey[dickey['start_speed'] < 60]), 'under 60 mph'

over_60 = baseball['start_speed'] >= 60
baseball = baseball[over_60]

baseball = baseball[['pitch_time', 'inning', 'pitcher_name', 'hitter_name', 'pitch_type', 
         'px', 'pz', 'pitch_name', 'start_speed', 'end_speed', 'type_confidence']]
baseball.head()

p = ggplot(aes(x='px', y='pz', color='pitch_name'), data=baseball) + geom_jitter()
p

p = ggplot(aes(x='px', y='pz'), data=baseball) + geom_point(color='blue') + facet_wrap('pitch_name')
p

baseball['pitch_name'].value_counts()

# Show in percentages
baseball['pitch_name'].value_counts() / len(baseball) * 100

from IPython.display import YouTubeVideo
YouTubeVideo('uW0V6OsxDBo', 600, 338)

p = ggplot(aes(x='start_speed'), data=baseball) + geom_histogram() + facet_wrap('pitch_name')
p

# Let's see how many of these Dickey throws
knuckles = baseball[baseball['pitch_name'] == 'Knuckleball']
dickey = knuckles[knuckles['pitcher_name'] == 'R.A. Dickey']
print 'Percentage of Knuckleballs belonging to Dickey', (len(dickey) / len(knuckles) * 100)

# Let's get darvish data
darvish = baseball[baseball['pitcher_name'] == 'Yu Darvish']
darvish['pitch_name'].value_counts() / len(darvish) * 100

p = ggplot(aes(x='px', y='pz', color='pitch_name'), data=darvish) + geom_jitter(alpha=0.3)
p = p + ggtitle('Darvish Pitch Spread') + stat_smooth(method='lm')
p

p = ggplot(aes(x='inning', y='start_speed', color='pitch_name'), data=darvish)
p = p + stat_smooth(method='lm', size=5)
p

p = ggplot(aes(x='inning', y='start_speed', color='pitch_name'), data=darvish)
p = p + geom_jitter(alpha=0.3)
p

baseball['pitcher_name'].value_counts()

verlander = baseball[baseball['pitcher_name'] == 'Justin Verlander']
verlander.head()

verlander['pitch_name'].value_counts() / len(verlander) * 100

p = ggplot(aes(x='px', y='pz', color='pitch_name'), data=verlander) + geom_jitter(alpha=0.3)
p = p + ggtitle('Verlander Pitch Spread') + stat_smooth(method='lm')
p

p = ggplot(aes(x='inning', y='start_speed', color='pitch_name'), data=verlander)
p = p + stat_smooth(method='lm', size=5)
p

p = ggplot(aes(x='inning', y='start_speed', color='pitch_name'), data=verlander)
p = p + geom_jitter(alpha=0.3)
p

p = ggplot(aes(x='inning', y='start_speed', color='pitch_name'), data=baseball)
p = p + stat_smooth(method='lm', size=5) + ggtitle('Pitch Speed vs Innings')
p

p = ggplot(aes(x='inning', y='start_speed'), data=baseball)
p = p + stat_smooth(method='lm', size=5) + ggtitle('Pitch speed vs Innings')
p

baseball['date'] = baseball['pitch_time'].str.slice(0,10)
baseball['pitch_count'] = 1
baseball['pitch_count'] = baseball.groupby(['pitcher_name', 'date'])['pitch_count'].cumsum()

p = ggplot(aes(x='pitch_count', y='start_speed', color='pitch_name'), data=baseball)
p = p + stat_smooth(method='lm', size=5) + ggtitle('Pitch Speed vs Pitch Count')
p

p = ggplot(aes(x='pitch_count', y='start_speed'), data=baseball)
p = p + stat_smooth(method='lm', size=5) + ggtitle('Pitch Speed vs Pitch Count')
p

darvish = baseball[baseball['pitcher_name'] == 'Yu Darvish']
p = ggplot(aes(x='pitch_count', y='start_speed', color='pitch_name'), data=darvish)
p = p + stat_smooth(se=False, size=5) + geom_jitter(alpha=0.3) 
p = p + ggtitle('Darvish: Pitch Speed vs Pitch Count')
p

verlander = baseball[baseball['pitcher_name'] == 'Justin Verlander']
p = ggplot(aes(x='pitch_count', y='start_speed', color='pitch_name'), data=verlander)
p = p + stat_smooth(se=False, size=5) + geom_jitter(alpha=0.3) 
p = p + ggtitle('Verlander: Pitch Speed vs Pitch Count')
p

# Let's see if anyone else's fastball speed increases over time!
fastballs = baseball[baseball['pitch_name'] == 'Fastball']
top10 = set(fastballs.pitcher_name.value_counts().index[:10])
pitchers = set(fastballs.pitcher_name)
for name in pitchers:
    if name not in top10:
        drop_rows = fastballs.index[fastballs.pitcher_name == name]
        fastballs = fastballs.drop(drop_rows, axis=0)

set(fastballs.pitcher_name)

p = ggplot(aes(x='pitch_count',y='start_speed'), data=fastballs) + stat_smooth(se=False, size=3)
p = p + facet_wrap('pitcher_name')
p

colon = baseball[baseball.pitcher_name == 'Bartolo Colon']
colon.pitch_name.value_counts() / len(colon) * 100