import pandas as pd
import seaborn as sns

%load_ext autoreload
%autoreload 2

data = pd.read_csv('http://datasets.flowingdata.com/ppg2008.csv', index_col=0)

# label source:https://en.wikipedia.org/wiki/Basketball_statistics
labels = ['Games','Minutes','Points','Field goals made','Field goal attempts','Field goal percentage','Free throws made','Free throws attempts','Free throws percentage','Three-pointers made','Three-point attempt','Three-point percentage','Offensive rebounds','Defensive rebounds','Total rebounds','Assists','Steals','Blocks','Turnover','Personal foul']
data.columns = labels

data

from seaborn.clustering import clusteredheatmap

data_normalized = data/data.max().astype(float)
data_normalized = (data_normalized - data_normalized.mean())/data_normalized.var()


clusteredheatmap(data_normalized);

from seaborn.clustering import clusteredheatmap

data_normalized = data/data.max().astype(float)
data_normalized = (data_normalized - data_normalized.mean())/data_normalized.var()


clusteredheatmap(data_normalized.T, col_kws={'fontsize': 18}, row_kws={'fontsize': 18});

from seaborn.clustering import clusteredheatmap

data_normalized = data/data.max().astype(float)
data_normalized = (data_normalized - data_normalized.mean())/data_normalized.var()


clusteredheatmap(data_normalized, col_kws={'fontsize': 18}, row_kws={'fontsize': 18});