%load_ext autoreload
%autoreload 2

import pandas as pd
from seaborn.clustering import clusterplot
import numpy as np
import string

shape = (10, 20)
np.random.seed(2013)
df = pd.DataFrame(np.random.randn(*shape), index=list(string.lowercase[0:shape[0]]), 
                  columns=list(string.uppercase[0:shape[1]]))

# -- Add some structure in the matrix so we can try to be correct -- #
# Add 5 to rows a,b,c,d,e and columns K,L,M,N,O,P,Q,R,S,T
df.ix[0:5,10:20] += 5

# Subtract 5 from rows f,g,h,i,j and columns A,B,C,D,E
df.ix[5:10,0:5] -= 5

fig, row_dendrogram, col_dendrogram = clusterplot(df)

import pandas as pd
import numpy as np
import string
import matplotlib as mpl
import brewer2mpl

shape = (10, 20)
np.random.seed(2013)
df = pd.DataFrame(np.random.randn(*shape), index=list(string.lowercase[0:shape[0]]), 
                  columns=list(string.uppercase[0:shape[1]]))

# -- Add some structure in the matrix so we can try to be correct -- #
# Add 5 to rows a,b,c,d,e and columns K,L,M,N,O,P,Q,R,S,T
df.ix[0:5,10:20] += 100

# Subtract 5 from rows f,g,h,i,j and columns A,B,C,D,E
df.ix[5:10,0:5] = np.random.uniform(high=0.001, size=(5,5))

# --- Crazy stuff starts here!!! ---
# Set the df to absolute so we can show log scaling
df = df.abs()

# Add some NAs
df.ix['c', 'C'] = np.nan
df_na_mean = df.fillna(df.mean())



vowels = ['a', 'e', 'i', 'o', 'u']
vowels += map(string.upper, vowels)
# print vowels

set1 = brewer2mpl.get_map('Set1', 'qualitative', 9).mpl_colors
grey = set1[8]
pink = set1[7]
col_side_colors = [pink if letter in vowels else grey for letter in df.columns]
row_side_colors = [pink if letter in vowels else grey for letter in df.index]


cmap = mpl.cm.YlGnBu
# highlight the NA with white
cmap.set_under('white')


fig, row_dendrogram, col_dendrogram = clusterplot(df=df_na_mean, 
                                                       title='Awesome heatmap example',
                                                       title_fontsize=32,
                                                       colorbar_label='powers of 10',
                                                       col_side_colors=col_side_colors,
                                                       row_side_colors=row_side_colors,
                                                       color_scale='log',
                                                       cmap=cmap,
                                                       linkage_method='single',
                                                       figsize=(20,10),
                                                       label_rows=[letter+'++' for letter in df.index],
                                                       label_cols=False,
                                                       xlabel_fontsize=8,
                                                       ylabel_fontsize=20,
                                                       cluster_rows=False,
                                                       cluster_cols=True,
                                                       vmin=1e-4, vmax=1e2,
                                                       plot_df=df, edgecolor='white', linewidth=0.01)