prasertcbs_pandas_viz_histogram.py

#-------------------------------------------------------------------------------------------------------------------
# Load standard libraries
# ------------------------------------------------------------------------------------------------------------------
import os
import pandas as pd
import numpy as np
import tqdm
import warnings
warnings.filterwarnings('ignore')
from datetime import timedelta
import monthdelta
from glob import glob
from functools import reduce
from IPython.core.interactiveshell import InteractiveShell
InteractiveShell.ast_node_interactivity = "all"
%config Completer.use_jedi = False
pd.options.display.max_rows = 999
pd.options.display.max_columns = 999 
from IPython.core.display import display, HTML
display(HTML("<style>.container { width:90% !important; }</style>"))
%matplotlib inline 
from IPython.display import display, HTML
pd.options.display.float_format = '{:20,.2f}'.format

# ------------------------------------------------------------------------------------------------------------------
# Load data visualizations
# ------------------------------------------------------------------------------------------------------------------
# matplotlib
import matplotlib.pyplot as plt
%matplotlib inline

# seaborn
import seaborn as sns; 
sns.set(style="whitegrid", color_codes=True)

# ------------------------------------------------------------------------------------------------------------------
# Load sample data
# ------------------------------------------------------------------------------------------------------------------
df=pd.read_csv('https://github.com/prasertcbs/tutorial/raw/master/mpg.csv')
df.head()
# manufacturer model  displ  year  cyl       trans drv  cty  hwy fl    class
# 0         audi    a4    1.8  1999    4    auto(l5)   f   18   29  p  compact
# 1         audi    a4    1.8  1999    4  manual(m5)   f   21   29  p  compact
# 2         audi    a4    2.0  2008    4  manual(m6)   f   20   31  p  compact
# 3         audi    a4    2.0  2008    4    auto(av)   f   21   30  p  compact
# 4         audi    a4    2.8  1999    6    auto(l5)   f   16   26  p  compact

# Plot the histogram for the numerical columns (pandas chooses it automatically)
df.hist()

# Plot the histogram for the specific numerical column
df.cty.hist()

# Plot the histogram for the specific numerical column and conceal the logging
df.cty.hist();

# Plot the histogram for the specific numerical column with 20 bins
df.cty.hist(bins=20);

# Plot the histogram for two columns where we can specify color and share the "axes" arguments
df[['cty', 'hwy']].hist(grid=True, color='orange', sharex=True, sharey=True)
plt.tight_layout()
plt.show();

# Plot the histogram for two columns altogether 
df[['cty', 'hwy']].plot.hist()
df[['cty', 'hwy']].plot.hist(alpha=.2)

# Plot the density (either density() or kde() works)
df.cty.plot.density()
df.cty.plot.kde()

# Plot the bar graph (count) for each class
df['class'].value_counts()
df['class'].value_counts().plot.bar()
df['class'].value_counts().plot.barh(color='orange')
df['class'].value_counts().plot.barh(color='.7')
df['class'].value_counts().sort_values().plot.barh(color='.7')