In [ ]:

    

import blaze as bz
import pandas as pd
import numpy as np
from into import into
from bokeh.plotting import *


    

In [ ]:

    

output_notebook()


    

In [ ]:

    

db = bz.Data('sqlite:///../lahman2013.sqlite')
db.dshape


    

In [ ]:

    

list(db.Salaries.teamID.distinct())


    

In [ ]:

    

r = bz.compute(db.Salaries["teamID"].distinct())
into(pd.DataFrame, r)


    

In [ ]:

    

result = bz.by(db.Salaries.teamID, avg=db.Salaries.salary.mean(), 
                                   max=db.Salaries.salary.max(), 
                                   ratio=db.Salaries.salary.max() / db.Salaries.salary.min()
                ).sort('ratio', ascending=False)
df = into(pd.DataFrame, result)


    

In [ ]:

    

df


    

In [ ]:

    

df = df.sort('avg')
source = ColumnDataSource(df)
p = figure(x_range=list(df["teamID"]))
p.scatter(x="teamID", y="avg", source=source)
show(p)


    

In [ ]:

    

df = df.sort('avg')
source = ColumnDataSource(df)
p = figure(x_range=list(df["teamID"]))
p.scatter(x="teamID", y="avg", source=source)
p.xaxis.major_label_orientation = np.pi/3

show(p)


    

In [ ]:

    

df = df.sort('avg')
source = ColumnDataSource(df)
s1 = figure(x_range=list(df["teamID"]))
s1.scatter(x="teamID", y="avg", source=source)
s1.xaxis.major_label_orientation = np.pi/3

s2 = figure(x_range=list(df["teamID"]))
s2.scatter(x="teamID", y="ratio", source=source)
s2.xaxis.major_label_orientation = np.pi/3

p = gridplot([[s1, s2]])
show(p)


    

In [ ]:

    

TOOLS = "pan,wheel_zoom,box_zoom,reset,save,box_select,lasso_select"

df = df.sort('avg')
source = ColumnDataSource(df)
s1 = figure(x_range=list(df["teamID"]), tools=TOOLS)
s1.scatter(x="teamID", y="avg", source=source)
s1.xaxis.major_label_orientation = np.pi/3

s2 = figure(x_range=list(df["teamID"]), tools=TOOLS)
s2.scatter(x="teamID", y="ratio", source=source)
s2.xaxis.major_label_orientation = np.pi/3

p = gridplot([[s1],[s2]])
show(p)


    

In [ ]:

    

db.Salaries.dshape


    

In [ ]:

    

db.Salaries[db.Salaries.yearID == 2012]


    

In [ ]:

    

#r = bz.compute(db.Salaries[db.Salaries.yearID == 2012])
#df = into(pd.DataFrame, r)
df = into(pd.DataFrame, db.Salaries)
df = df[df["teamID"] == "LAA"]
df = df[df["yearID"] == 2012]
df


    

In [ ]:

    

TOOLS = "pan,wheel_zoom,box_zoom,reset,save,box_select,lasso_select"

source = ColumnDataSource(df)
p = figure(x_range=list(df["playerID"]), tools=TOOLS)
p.scatter(x="playerID", y="salary", source=source)
p.xaxis.major_label_orientation = np.pi/3

show(p)


    

In [ ]:

    

TOOLS = "pan,wheel_zoom,box_zoom,reset,save,box_select,lasso_select"

df = df.sort('salary')
source = ColumnDataSource(df)
p = figure(x_range=list(df["playerID"]), tools=TOOLS)
p.scatter(x="playerID", y="salary", source=source)
p.xaxis.major_label_orientation = np.pi/3

show(p)


    

In [ ]: