prasertcbs_pandas_viz_scatter.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
%config InlineBackend.figure_format = 'retina' # Set as High-Definition (HD) Image

# 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.sample(5)
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 basic scatterplot
df.plot.scatter(x='displ', y='cty')

# Plot the basic scatterplot with 
%config InlineBackend.figure_format = 'retina' # Set as High-Definition (HD) Image
df.plot.scatter(x='displ', y='cty')

# Plot the basic scatterplot with grid and title
df.plot.scatter(x='displ', y='cty', grid=True, title='City miles per gallon vs. engine size (litres)');

# More advanced one...
# Plot the scatterplot based on the categorical variable (in this case, it's df['drv'])
df.plot.scatter(x='displ', y='cty', 
                grid=True, 
                c=df.drv.map({'4':'green', 'f':'blue', 'r':'red'}),
                title='City miles per gallon vs. engine size (litres)');

df.plot.scatter(x='displ', y='cty', 
                grid=True, 
                c=df.drv.map({'4':'green', 'f':'blue', 'r':'red'}),
                s=df.displ*10,
                title='City miles per gallon vs. engine size (litres)');

df.plot.scatter(x='displ', y='cty', 
                grid=True, 
                c=df.drv.map({'4':'green', 'f':'blue', 'r':'red'}),
                s=df.cyl*10,
                title='City miles per gallon vs. engine size (litres)');

df.plot.scatter(x='displ', y='cty', 
                grid=True, 
                c=df.drv.map({'4':'green', 'f':'blue', 'r':'red'}),
                s=df.cyl*10,
                alpha=.5,
                title='City miles per gallon vs. engine size (litres)');

df.plot.scatter(x='displ', y='cty', 
                grid=True, 
                c=df.drv.map({'4':'green', 'f':'blue', 'r':'red'}),
                s=30,
                alpha=.5,
                title='City miles per gallon vs. engine size (litres)');

df.plot.scatter(x='displ', y='cty', 
                grid=True, 
                c=df.drv.map({'4':'green', 'f':'blue', 'r':'red'}),
                s=df.cyl*10,
                alpha=.5,
                ylim=(0, 40),
                xlim=(0, 10),
                title='City miles per gallon vs. engine size (litres)');