6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [2]: import pandas as pd

import matplotlib.pyplot as plt
import numpy as np
import seaborn as sns
from sklearn.pipeline import Pipeline
from sklearn.preprocessing import StandardScaler,PolynomialFeatures
%matplotlib inline

In [3]: file_name='https://s3-api.us-geo.objectstorage.softlayer.net/cf-courses-data/CognitiveClass/DA0101EN/coursera/project/
df=pd.read_csv(file_name)

In [4]: df.head()

Out[4]:
Unnamed:
id date price bedrooms bathrooms sqft_living sqft_lot floors waterfront ... grade sqft_above sqft_
0

0 0 7129300520 20141013T000000 221900.0 3.0 1.00 1180 5650 1.0 0 ... 7 1180

1 1 6414100192 20141209T000000 538000.0 3.0 2.25 2570 7242 2.0 0 ... 7 2170

2 2 5631500400 20150225T000000 180000.0 2.0 1.00 770 10000 1.0 0 ... 6 770

3 3 2487200875 20141209T000000 604000.0 4.0 3.00 1960 5000 1.0 0 ... 7 1050

4 4 1954400510 20150218T000000 510000.0 3.0 2.00 1680 8080 1.0 0 ... 8 1680

5 rows × 22 columns

localhost:8888/notebooks/Data Analysis with Python.ipynb# 1/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [6]: print(df.dtypes)

Unnamed: 0 int64
id int64
date object
price float64
bedrooms float64
bathrooms float64
sqft_living int64
sqft_lot int64
floors float64
waterfront int64
view int64
condition int64
grade int64
sqft_above int64
sqft_basement int64
yr_built int64
yr_renovated int64
zipcode int64
lat float64
long float64
sqft_living15 int64
sqft_lot15 int64
dtype: object

localhost:8888/notebooks/Data Analysis with Python.ipynb# 2/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [7]: df.describe()

Out[7]:
Unnamed: 0 id price bedrooms bathrooms sqft_living sqft_lot floors waterfront vi

count 21613.00000 2.161300e+04 2.161300e+04 21600.000000 21603.000000 21613.000000 2.161300e+04 21613.000000 21613.000000 21613.0000

mean 10806.00000 4.580302e+09 5.400881e+05 3.372870 2.115736 2079.899736 1.510697e+04 1.494309 0.007542 0.2343

std 6239.28002 2.876566e+09 3.671272e+05 0.926657 0.768996 918.440897 4.142051e+04 0.539989 0.086517 0.7663

min 0.00000 1.000102e+06 7.500000e+04 1.000000 0.500000 290.000000 5.200000e+02 1.000000 0.000000 0.0000

25% 5403.00000 2.123049e+09 3.219500e+05 3.000000 1.750000 1427.000000 5.040000e+03 1.000000 0.000000 0.0000

50% 10806.00000 3.904930e+09 4.500000e+05 3.000000 2.250000 1910.000000 7.618000e+03 1.500000 0.000000 0.0000

75% 16209.00000 7.308900e+09 6.450000e+05 4.000000 2.500000 2550.000000 1.068800e+04 2.000000 0.000000 0.0000

max 21612.00000 9.900000e+09 7.700000e+06 33.000000 8.000000 13540.000000 1.651359e+06 3.500000 1.000000 4.0000

8 rows × 21 columns

In [8]: df.drop(['id', 'Unnamed: 0'], axis=1, inplace=True)

df.describe()

Out[8]:
price bedrooms bathrooms sqft_living sqft_lot floors waterfront view condition gr

count 2.161300e+04 21600.000000 21603.000000 21613.000000 2.161300e+04 21613.000000 21613.000000 21613.000000 21613.000000 21613.000

mean 5.400881e+05 3.372870 2.115736 2079.899736 1.510697e+04 1.494309 0.007542 0.234303 3.409430 7.656

std 3.671272e+05 0.926657 0.768996 918.440897 4.142051e+04 0.539989 0.086517 0.766318 0.650743 1.175

min 7.500000e+04 1.000000 0.500000 290.000000 5.200000e+02 1.000000 0.000000 0.000000 1.000000 1.000

25% 3.219500e+05 3.000000 1.750000 1427.000000 5.040000e+03 1.000000 0.000000 0.000000 3.000000 7.000

50% 4.500000e+05 3.000000 2.250000 1910.000000 7.618000e+03 1.500000 0.000000 0.000000 3.000000 7.000

75% 6.450000e+05 4.000000 2.500000 2550.000000 1.068800e+04 2.000000 0.000000 0.000000 4.000000 8.000

max 7.700000e+06 33.000000 8.000000 13540.000000 1.651359e+06 3.500000 1.000000 4.000000 5.000000 13.000

localhost:8888/notebooks/Data Analysis with Python.ipynb# 3/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [9]: print("number of NaN values for the column bedrooms :", df['bedrooms'].isnull().sum())
print("number of NaN values for the column bathrooms :", df['bathrooms'].isnull().sum())

number of NaN values for the column bedrooms : 13

number of NaN values for the column bathrooms : 10

In [11]: mean=df['bedrooms'].mean()
df['bedrooms'].replace(np.nan,mean, inplace=True)

In [12]: mean=df['bathrooms'].mean()
df['bathrooms'].replace(np.nan,mean, inplace=True)

In [13]: print("number of NaN values for the column bedrooms :", df['bedrooms'].isnull().sum())
print("number of NaN values for the column bathrooms :", df['bathrooms'].isnull().sum())

number of NaN values for the column bedrooms : 0

number of NaN values for the column bathrooms : 0

In [14]: df['floors'].value_counts().to_frame()

Out[14]:
floors

1.0 10680

2.0 8241

1.5 1910

3.0 613

2.5 161

3.5 8

localhost:8888/notebooks/Data Analysis with Python.ipynb# 4/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [15]: sns.boxplot(x='waterfront', y='price', data=df)

Out[15]: <AxesSubplot:xlabel='waterfront', ylabel='price'>

localhost:8888/notebooks/Data Analysis with Python.ipynb# 5/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [16]: sns.regplot(x='sqft_above', y='price', data=df)

Out[16]: <AxesSubplot:xlabel='sqft_above', ylabel='price'>

localhost:8888/notebooks/Data Analysis with Python.ipynb# 6/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [17]: df.corr()['price'].sort_values()

Out[17]: zipcode -0.053203

long 0.021626
condition 0.036362
yr_built 0.054012
sqft_lot15 0.082447
sqft_lot 0.089661
yr_renovated 0.126434
floors 0.256794
waterfront 0.266369
lat 0.307003
bedrooms 0.308797
sqft_basement 0.323816
view 0.397293
bathrooms 0.525738
sqft_living15 0.585379
sqft_above 0.605567
grade 0.667434
sqft_living 0.702035
price 1.000000
Name: price, dtype: float64

In [18]: import matplotlib.pyplot as plt

from sklearn.linear_model import LinearRegression
​
X = df[['long']]
Y = df['price']
lm = LinearRegression()
lm
lm.fit(X,Y)
lm.score(X, Y)

Out[18]: 0.00046769430149007363

localhost:8888/notebooks/Data Analysis with Python.ipynb# 7/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [19]: X = df[['sqft_living']]
Y = df['price']
lm = LinearRegression()
lm.fit(X, Y)
lm.score(X, Y)

Out[19]: 0.4928532179037931

In [21]: features =["floors", "waterfront","lat" ,"bedrooms" ,"sqft_basement" ,"view" ,"bathrooms","sqft_living15","sqft_above"

In [22]: X = df[features]
Y= df['price']
lm = LinearRegression()
lm.fit(X, Y)
lm.score(X, Y)

Out[22]: 0.6576435664044019

In [23]: Input=[('scale',StandardScaler()),('polynomial', PolynomialFeatures(include_bias=False)),('model',LinearRegression())]

In [24]: pipe=Pipeline(Input)
pipe

Out[24]: Pipeline(steps=[('scale', StandardScaler()),

('polynomial', PolynomialFeatures(include_bias=False)),
('model', LinearRegression())])

In [25]: pipe.fit(X,Y)

Out[25]: Pipeline(steps=[('scale', StandardScaler()),

('polynomial', PolynomialFeatures(include_bias=False)),
('model', LinearRegression())])

localhost:8888/notebooks/Data Analysis with Python.ipynb# 8/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [26]: pipe.score(X,Y)

Out[26]: 0.750441999451871

In [27]: from sklearn.model_selection import cross_val_score

from sklearn.model_selection import train_test_split
print("done")

done

In [28]: features =["floors", "waterfront","lat" ,"bedrooms" ,"sqft_basement" ,"view" ,"bathrooms","sqft_living15","sqft_above"

X = df[features ]
Y = df['price']
​
x_train, x_test, y_train, y_test = train_test_split(X, Y, test_size=0.15, random_state=1)
​
​
print("number of test samples :", x_test.shape[0])
print("number of training samples:",x_train.shape[0])

number of test samples : 3242

number of training samples: 18371

In [29]: from sklearn.linear_model import Ridge

​
RidgeModel = Ridge(alpha = 0.1)
RidgeModel.fit(x_train, y_train)
RidgeModel.score(x_test, y_test)

Out[29]: 0.6478759163939111

localhost:8888/notebooks/Data Analysis with Python.ipynb# 9/10

6/8/23, 1:10 PM Data Analysis with Python - Jupyter Notebook

In [30]: from sklearn.preprocessing import PolynomialFeatures

from sklearn.linear_model import Ridge
pr = PolynomialFeatures(degree=2)
x_train_pr = pr.fit_transform(x_train)
x_test_pr = pr.fit_transform(x_test)
poly = Ridge(alpha=0.1)
poly.fit(x_train_pr, y_train)
poly.score(x_test_pr, y_test)

Out[30]: 0.7002744282813562

In [ ]: ​

localhost:8888/notebooks/Data Analysis with Python.ipynb# 10/10