# step 1: Set up the matplotlib figure, 3 rows X 3 columns
f, axes = plt.subplots(3, 3, ...)
# step 2: instantiae a python zip object with 2 parameters
# parameter 1: axes.flat,
# it has 9 MAT subplots.
# parameter 2: np.linspace(0, 3, 10)) evenly separated
# 0.00, 0.33, 0.66, 1.00, 1.33, 1.66, 2.00, 2.33, 2.66, 3.00
# 9 will be used in the loop for palette color configuration.
# step 3: loop the zip
# for each iteration
# - create a cmap, using s value
# - Generate a random bivariate dataset,
# x, y = rs.randn(2, 50)
# two dimension nparray
# 50 points
# step 4: plot it with method kdeplot
# - different data
# - different palette
import numpy as np
import pandas as pd
# --- step 1, using numpy to generate data
r = np.linspace(0, 10, num=100)
print(' r = ' + str(r))
# r = [ 0. 0.1 0.2 1.0 2.0... 9.8, 10.0 ]
# 100 number, evenly separated.
# --- step 2, using pandas to create a dataframe - wide form
df = pd.DataFrame({'r': r, 'slow': r, 'medium': 2 * r, 'fast': 4 * r})
print('df = ' + str(df))
print('df.shape = ' + str(df.shape))
'''
r slow medium fast
0 0.000000 0.000000 0.000000 0.000000
1 0.101010 0.101010 0.202020 0.404040
100 rows, 4 columns
'''
# --- step 3, using pandas melt method to convert to long form
#The plotting method expects lon-form format.
df2 = pd.melt(df, id_vars=['r'], var_name='speed', value_name='theta')
print('df2 = ' + str(df2))
print('df2.shape = ' + str(df2.shape))
'''
r speed theta
0 0.000000 slow 0.000000
1 0.101010 slow 0.101010
300 rows, 3 columns
'''
tips = sns.load_dataset("tips")
g = sns.FacetGrid(tips, row="sex", col="time", margin_titles=True)
bins = np.linspace(0, 60, 13)
g.map(plt.hist, "total_bill", color="steelblue", bins=bins)
------------- step 1: examine the data... ------------------------------
df = sns.load_dataset("brain_networks", header=[0, 1, 2], index_col=0)
used_networks = [1, 5, 6, 7, 8, 12, 13, 17]
used_columns = (df.columns.get_level_values("network")
.astype(int)
.isin(used_networks))
df = df.loc[:, used_columns]
print('df')
'''
network 1 5 ...17
node 1 1 ...
hemi lh rh lh rh ...
0 56.055744 92.031036 -35.898861 -1.889181...
1 55.547253 43.690075 19.568010 15.902983...
'''
note 1: There are 3 lines for dataframe heading.
note 2: The hierarchy of brain networks data are network, node, left or right.
note 3: the values are like 56.0, 15.90... for each hemi
-------------------- step 2: generate the corrections form the data ----
df.corr() is the function argument in method sns.clustermap.
It genenerates correlations from the data.
'''
network 1 5
node 1 1
hemi lh rh lh rh
network node hemi
1 1 lh 1.000000 0.881516 0.431619 0.418708
rh 0.881516 1.000000 0.431953 0.519916
5 1 lh 0.431619 0.431953 1.000000 0.822897
rh 0.418708 0.519916 0.822897 1.000000
'''
note 1: The values are like 0.88, 0.5, 1...
note 2: 1 means 100% correlation, it refers itself.
note 3: 0 means no correlation.
note 4: minus means opposite correlations.
The following is the wide-form dataset.
A B C D
2016-01-01 0.167921 0.523505 0.817376 1.703846
2016-01-02 -1.979026 1.237704 0.057230 2.743267
....