02-HighLevelCharts.tex

%nbviewer
%FAQ
%IPython
%Jupyter
%bokeh-notebooks   tutorial
%===========================================================================================================%	
\section{Bokeh Tutorial — \texttt{bokeh.charts} interface}
\begin{framed}
	\begin{verbatim}
In [1]:
import numpy as np
import pandas as pd
from bokeh.io import output_notebook, show
\end{verbatim}
\end{framed}
%===========================================================================================================%	
\begin{framed}
\begin{verbatim}
In [2]:
output_notebook()
BokehJS successfully loaded.
\end{verbatim}
\end{framed}
%===========================================================================================================%	
\begin{framed}
	\begin{verbatim}
In [3]:
from bokeh.charts import Scatter
from bokeh.sampledata.iris import flowers

# fill a data frame with the data of interest and create a groupby object
df = flowers[["petal_length", "petal_width", "species"]]
xyvalues = df.groupby("species")

# any of the following commented are also valid Scatter inputs
#xyvalues = pd.DataFrame(xyvalues)
#xyvalues = xyvalues.values()
#xyvalues = np.array(xyvalues.values())

TOOLS="resize,crosshair,pan,wheel_zoom,box_zoom,reset,previewsave"

scatter = Scatter(xyvalues, tools=TOOLS, ylabel='petal_width')

show(scatter)
inspect 
\end{verbatim}
\end{framed}
%===========================================================================================================%	
\begin{framed}
\begin{verbatim}	
In [4]:
from bokeh.charts import Bar
from bokeh.sampledata.olympics2014 import data

df = pd.io.json.json_normalize(data['data'])

# filter by countries with at least one medal and sort
df = df[df['medals.total'] > 0]
df = df.sort("medals.total", ascending=False)

# get the countries and we group the data by medal type
countries = df.abbr.values.tolist()
gold = df['medals.gold'].astype(float).values
silver = df['medals.silver'].astype(float).values
bronze = df['medals.bronze'].astype(float).values

# build a dict containing the grouped data
medals = pd.DataFrame(dict(bronze=bronze, silver=silver, gold=gold))

bar = Bar(medals, countries, title="Stacked bars", stacked=True)

show(bar)
\end{verbatim}
\end{framed}
%===========================================================================================================%	
\begin{framed}
\begin{verbatim}
In [5]:
from bokeh.charts import Histogram

# build some distributions and load them into a dict
mu, sigma = 0, 0.5
normal = np.random.normal(mu, sigma, 1000)
lognormal = np.random.lognormal(mu, sigma, 1000)

# create a pandas data frame from the dict
df = pd.DataFrame(dict(normal=normal, lognormal=lognormal))

hist = Histogram(df, bins=50, legend=True)

show(hist)
ERROR:/Users/bryan/anaconda/envs/bk092/lib/python3.4/site-packages/bokeh/validation/check.py:E-1000 (COLUMN_LENGTHS): ColumnDataSource column lengths are not all the same: ColumnDataSource, ViewModel:ColumnDataSource, ref _id: ec4ff74c-3a90-4ffc-be64-00b876c4df67
	
In [ ]:
\end{verbatim}
\end{framed}
%===========================================================================================================%	
\end{document}