Table of Contents

• 1  Data Description
• 2  Imports
• 3  Load the data
• 4  Correlation Heatmap
• 5  Univariate Analysis
  • 5.1  Categorical variable
  • 5.2  Continuous variables
    • 5.2.1  histograms
    • 5.2.2  distribution plots
    • 5.2.3  Box plots
• 6  Bi-variate Analysis
  • 6.1  Scatter plots
• 7  Multi-variate Analysis
  • 7.1  scatterplots
  • 7.2  Bubble plots
• 8  Map visualization

Kernel Author:
Bhishan Poudel, Data Scientist, Ph.D Astrophysics .

Data Description

This dataset contains house sale prices for King County, which includes Seattle. It includes homes sold between May 2014 and May 2015.

Imports

import numpy as np
import pandas as pd
import seaborn as sns
sns.set(color_codes=True)

import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline

import os
import time

# random state
SEED = 0
RNG = np.random.RandomState(SEED)

# Jupyter notebook settings for pandas
pd.set_option('display.max_columns', 50)
pd.set_option('display.float_format', '{:,.2g}'.format) # numbers sep by comma
pd.set_option('display.max_rows', 20) # None for all the rows
pd.set_option('display.max_colwidth', 50)

import IPython
from IPython.display import display

print([(x.__name__,x.__version__) for x in [np, pd,sns,matplotlib]])

[('numpy', '1.16.4'), ('pandas', '0.25.0'), ('seaborn', '0.9.0'), ('matplotlib', '3.1.1')]

import plotly
import plotly.offline as py
import plotly.graph_objs as go
import plotly.figure_factory as ff
import plotly.tools as tls
from plotly.offline import plot, iplot, init_notebook_mode
init_notebook_mode(connected=False)

[(x.__name__,x.__version__) for x in [plotly]]

[('plotly', '3.10.0')]

%load_ext autoreload
%autoreload 2

%%javascript
IPython.OutputArea.auto_scroll_threshold = 9999;

Load the data

df = pd.read_csv('../data/processed/data_cleaned_encoded.csv')
print(df.shape)
df.head().T

(21613, 92)

	0	1	2	3	4
id	7129300520	6414100192	5631500400	2487200875	1954400510
date	2014-10-13	2014-12-09	2015-02-25	2014-12-09	2015-02-18
price	2.2e+05	5.4e+05	1.8e+05	6e+05	5.1e+05
bedrooms	3	3	2	4	3
bathrooms	1	2.2	1	3	2
sqft_living	1180	2570	770	1960	1680
sqft_lot	5650	7242	10000	5000	8080
floors	1	2	1	1	1
waterfront	0	0	0	0	0
view	0	0	0	0	0
...	...	...	...	...	...
age_after_renovation_cat_7	0	0	1	0	0
age_after_renovation_cat_8	0	0	0	0	0
age_after_renovation_cat_9	0	0	0	0	0
log1p_price	12	13	12	13	13
log1p_sqft_living	7.1	7.9	6.6	7.6	7.4
log1p_sqft_lot	8.6	8.9	9.2	8.5	9
log1p_sqft_above	7.1	7.7	6.6	7	7.4
log1p_sqft_basement	0	6	0	6.8	0
log1p_sqft_living15	7.2	7.4	7.9	7.2	7.5
log1p_sqft_lot15	8.6	8.9	9	8.5	8.9

92 rows × 5 columns

Correlation Heatmap

from bhishan.util_viz_plotly import plotly_corr_heatmap

plotly_corr_heatmap(df,'price',show=False,
            ofile='../reports/html/correlation_heatmap.html',
              auto_open=True)

Univariate Analysis

Categorical variable

from bhishan.util_viz_plotly import plotly_countplot
plotly_countplot(df,'bedrooms',topN=5,show=False,
            ofile='../reports/html/countplot_grade.html',
              auto_open=True)

from bhishan.util_viz_plotly import plotly_countplot

plotly_countplot(df,'grade',topN=5,color='plum',show=False,
            ofile='../reports/html/countplot_grade.html',
              auto_open=True)

Continuous variables

histograms

from bhishan.util_viz_plotly import plotly_histogram

plotly_histogram(df,'sqft_living',show=False,
            ofile='../reports/html/histogram_sqft_living.html',
              auto_open=True)

from bhishan.util_viz_plotly import plotly_histogram

plotly_histogram(df,'yr_built',size=1,color='orchid',show=False,
            ofile='../reports/html/histogram_yr_built.html',
              auto_open=True)

distribution plots

sns.distplot(df['sqft_living'], hist=True, kde=True, rug=False,
             norm_hist=True, kde_kws={"label": "sqrt_living"})

<matplotlib.axes._subplots.AxesSubplot at 0x11c3576d8>

from bhishan.util_viz_plotly import plotly_distplot

cols = 'sqft_living'
plotly_distplot(df, cols,show=False,
            ofile='../reports/html/distplot_sqft_living.html',
              auto_open=True)

Box plots

sns.boxplot(y=df['price'])

<matplotlib.axes._subplots.AxesSubplot at 0x120b56438>

from bhishan.util_viz_plotly import plotly_boxplot
col = 'price'
plotly_boxplot(df,col,show=False,
            ofile='../reports/html/boxplot_price.html',
              auto_open=True)

sns.boxplot(x=df['bedrooms'],y=df['price'])

<matplotlib.axes._subplots.AxesSubplot at 0x12059c2b0>

from bhishan.util_viz_plotly import plotly_boxplot_categorical_column

plotly_boxplot_categorical_column(df,'bedrooms','price',show=False,
            ofile='../reports/html/boxplot_bedrooms_vs_price.html',
              auto_open=True)

from bhishan.util_viz_plotly import plotly_boxplot

plotly_boxplot(df,['bedrooms','bathrooms','floors'],ylim_lst=[0,13],
              show=False,ofile='../reports/html/boxplot_bedrooms_bathrooms_floors.html',
              auto_open=True)

Bi-variate Analysis

Scatter plots

from bhishan.util_viz_plotly import plotly_scattergl_plot   

xcol = 'sqft_living15'
ycol = 'price'
color = 'grade'
colorscale = 'Reds'
plotly_scattergl_plot(df,xcol,ycol,logy=True,bestfit=True,
                      color=color,colorscale=colorscale,
                     show=False,auto_open=True,
                     ofile='../reports/html/sqft_living15_vs_price_wrt_grade.html')

import seaborn as sns

sns.regplot(df.sqft_living15, np.log(df.price))

<matplotlib.axes._subplots.AxesSubplot at 0x1209feb70>

Multi-variate Analysis

scatterplots

from bhishan.util_viz_plotly import plotly_scattergl_plot_colorcol
   
plotly_scattergl_plot_colorcol(df,'sqft_living15','price',
                               colorcol='bedrooms',logy=True,show=False,
                              ofile='../reports/html/sqft_living15_vs_price.html',
                              auto_open=True)

from bhishan.util_viz_plotly import plotly_scattergl_plot_subplots
    

subplot_cols=['bedrooms', 'bathrooms', 'condition', 'grade', 'waterfront']

plotly_scattergl_plot_subplots(df,'sqft_living15','price',
                               subplot_cols,logy=True,
                              show=False,
                              ofile='../reports/html/categorical_subplots.html')

This is the format of your plot grid:
[ (1,1) x1,y1 ]
[ (2,1) x2,y2 ]
[ (3,1) x3,y3 ]
[ (4,1) x4,y4 ]
[ (5,1) x5,y5 ]

Bubble plots

from bhishan.util_viz_plotly import  plotly_bubbleplot

df1 = df[df.yr_built == 2014]
plotly_bubbleplot(df1, 'grade', 'bedrooms', 'bathrooms', 'floors',
                  size_factor=6,show=False,
                  ofile='../reports/html/bubbleplot1.html')

from bhishan.util_viz_plotly import plotly_bubbleplot

df1 = df[df.yr_built == 2015]
plotly_bubbleplot(df1, 'grade', 'bedrooms', 'bathrooms', 'floors',
                  size_factor=5,show=False,
                  ofile='../reports/html/bubbleplot2.html')

Map visualization

# select your dataframe
df1 = df.query(""" grade >= 7 and yr_built >= 2000 """)[['lat','long','grade','yr_built','price']].copy()

# create new column of text
df1['text'] = (  "Grade:" + df1.grade.apply(str) 
                + " Built Year:"+ df1.yr_built.apply(str)
                + " Price:"+ df1.price.apply(str)
               )

df1.head()

	lat	long	grade	yr_built	price	text
5	48	-1.2e+02	11	2001	1.2e+06	Grade:11 Built Year:2001 Price:1225000.0
9	47	-1.2e+02	7	2003	3.2e+05	Grade:7 Built Year:2003 Price:323000.0
29	48	-1.2e+02	8	2005	7.2e+05	Grade:8 Built Year:2005 Price:719000.0
30	48	-1.2e+02	8	2003	5.8e+05	Grade:8 Built Year:2003 Price:580500.0
31	48	-1.2e+02	7	2005	2.8e+05	Grade:7 Built Year:2005 Price:280000.0

from bhishan.util_viz_plotly import plotly_mapbox

plotly_mapbox(df1, 'lat', 'long', color_col='grade',
              ofile='../reports/html/mymap.html',
              show=False)

<span style="background:#2f4f4f"> Grade 11 </span> <span style="background:#800000"> Grade 7 </span> <span style="background:#006400"> Grade 8 </span> <span style="background:#000080"> Grade 9 </span> <span style="background:#9acd32"> Grade 10 </span> <span style="background:#ff0000"> Grade 12 </span> <span style="background:#ff8c00"> Grade 13 </span>

Grade 11 Grade 7 Grade 8 Grade 9 Grade 10 Grade 12 Grade 13