Contents:

import pandas as pd
import missingno as msno
import matplotlib.pyplot as plt
import seaborn as sns

Data Source: https://www.kaggle.com/c/house-prices-advanced-regression-techniques/data?select=train.csv

df = pd.read_csv('../Datasets/housing_train.csv')

df.head()
Id MSSubClass MSZoning LotFrontage LotArea Street Alley LotShape LandContour Utilities ... PoolArea PoolQC Fence MiscFeature MiscVal MoSold YrSold SaleType SaleCondition SalePrice
0 1 60 RL 65.0 8450 Pave NaN Reg Lvl AllPub ... 0 NaN NaN NaN 0 2 2008 WD Normal 208500
1 2 20 RL 80.0 9600 Pave NaN Reg Lvl AllPub ... 0 NaN NaN NaN 0 5 2007 WD Normal 181500
2 3 60 RL 68.0 11250 Pave NaN IR1 Lvl AllPub ... 0 NaN NaN NaN 0 9 2008 WD Normal 223500
3 4 70 RL 60.0 9550 Pave NaN IR1 Lvl AllPub ... 0 NaN NaN NaN 0 2 2006 WD Abnorml 140000
4 5 60 RL 84.0 14260 Pave NaN IR1 Lvl AllPub ... 0 NaN NaN NaN 0 12 2008 WD Normal 250000

5 rows × 81 columns

df.describe()
Id MSSubClass LotFrontage LotArea OverallQual OverallCond YearBuilt YearRemodAdd MasVnrArea BsmtFinSF1 ... WoodDeckSF OpenPorchSF EnclosedPorch 3SsnPorch ScreenPorch PoolArea MiscVal MoSold YrSold SalePrice
count 1460.000000 1460.000000 1201.000000 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000 1452.000000 1460.000000 ... 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000 1460.000000
mean 730.500000 56.897260 70.049958 10516.828082 6.099315 5.575342 1971.267808 1984.865753 103.685262 443.639726 ... 94.244521 46.660274 21.954110 3.409589 15.060959 2.758904 43.489041 6.321918 2007.815753 180921.195890
std 421.610009 42.300571 24.284752 9981.264932 1.382997 1.112799 30.202904 20.645407 181.066207 456.098091 ... 125.338794 66.256028 61.119149 29.317331 55.757415 40.177307 496.123024 2.703626 1.328095 79442.502883
min 1.000000 20.000000 21.000000 1300.000000 1.000000 1.000000 1872.000000 1950.000000 0.000000 0.000000 ... 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 1.000000 2006.000000 34900.000000
25% 365.750000 20.000000 59.000000 7553.500000 5.000000 5.000000 1954.000000 1967.000000 0.000000 0.000000 ... 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 0.000000 5.000000 2007.000000 129975.000000
50% 730.500000 50.000000 69.000000 9478.500000 6.000000 5.000000 1973.000000 1994.000000 0.000000 383.500000 ... 0.000000 25.000000 0.000000 0.000000 0.000000 0.000000 0.000000 6.000000 2008.000000 163000.000000
75% 1095.250000 70.000000 80.000000 11601.500000 7.000000 6.000000 2000.000000 2004.000000 166.000000 712.250000 ... 168.000000 68.000000 0.000000 0.000000 0.000000 0.000000 0.000000 8.000000 2009.000000 214000.000000
max 1460.000000 190.000000 313.000000 215245.000000 10.000000 9.000000 2010.000000 2010.000000 1600.000000 5644.000000 ... 857.000000 547.000000 552.000000 508.000000 480.000000 738.000000 15500.000000 12.000000 2010.000000 755000.000000

8 rows × 38 columns

df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 1460 entries, 0 to 1459
Data columns (total 81 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   Id             1460 non-null   int64  
 1   MSSubClass     1460 non-null   int64  
 2   MSZoning       1460 non-null   object 
 3   LotFrontage    1201 non-null   float64
 4   LotArea        1460 non-null   int64  
 5   Street         1460 non-null   object 
 6   Alley          91 non-null     object 
 7   LotShape       1460 non-null   object 
 8   LandContour    1460 non-null   object 
 9   Utilities      1460 non-null   object 
 10  LotConfig      1460 non-null   object 
 11  LandSlope      1460 non-null   object 
 12  Neighborhood   1460 non-null   object 
 13  Condition1     1460 non-null   object 
 14  Condition2     1460 non-null   object 
 15  BldgType       1460 non-null   object 
 16  HouseStyle     1460 non-null   object 
 17  OverallQual    1460 non-null   int64  
 18  OverallCond    1460 non-null   int64  
 19  YearBuilt      1460 non-null   int64  
 20  YearRemodAdd   1460 non-null   int64  
 21  RoofStyle      1460 non-null   object 
 22  RoofMatl       1460 non-null   object 
 23  Exterior1st    1460 non-null   object 
 24  Exterior2nd    1460 non-null   object 
 25  MasVnrType     1452 non-null   object 
 26  MasVnrArea     1452 non-null   float64
 27  ExterQual      1460 non-null   object 
 28  ExterCond      1460 non-null   object 
 29  Foundation     1460 non-null   object 
 30  BsmtQual       1423 non-null   object 
 31  BsmtCond       1423 non-null   object 
 32  BsmtExposure   1422 non-null   object 
 33  BsmtFinType1   1423 non-null   object 
 34  BsmtFinSF1     1460 non-null   int64  
 35  BsmtFinType2   1422 non-null   object 
 36  BsmtFinSF2     1460 non-null   int64  
 37  BsmtUnfSF      1460 non-null   int64  
 38  TotalBsmtSF    1460 non-null   int64  
 39  Heating        1460 non-null   object 
 40  HeatingQC      1460 non-null   object 
 41  CentralAir     1460 non-null   object 
 42  Electrical     1459 non-null   object 
 43  1stFlrSF       1460 non-null   int64  
 44  2ndFlrSF       1460 non-null   int64  
 45  LowQualFinSF   1460 non-null   int64  
 46  GrLivArea      1460 non-null   int64  
 47  BsmtFullBath   1460 non-null   int64  
 48  BsmtHalfBath   1460 non-null   int64  
 49  FullBath       1460 non-null   int64  
 50  HalfBath       1460 non-null   int64  
 51  BedroomAbvGr   1460 non-null   int64  
 52  KitchenAbvGr   1460 non-null   int64  
 53  KitchenQual    1460 non-null   object 
 54  TotRmsAbvGrd   1460 non-null   int64  
 55  Functional     1460 non-null   object 
 56  Fireplaces     1460 non-null   int64  
 57  FireplaceQu    770 non-null    object 
 58  GarageType     1379 non-null   object 
 59  GarageYrBlt    1379 non-null   float64
 60  GarageFinish   1379 non-null   object 
 61  GarageCars     1460 non-null   int64  
 62  GarageArea     1460 non-null   int64  
 63  GarageQual     1379 non-null   object 
 64  GarageCond     1379 non-null   object 
 65  PavedDrive     1460 non-null   object 
 66  WoodDeckSF     1460 non-null   int64  
 67  OpenPorchSF    1460 non-null   int64  
 68  EnclosedPorch  1460 non-null   int64  
 69  3SsnPorch      1460 non-null   int64  
 70  ScreenPorch    1460 non-null   int64  
 71  PoolArea       1460 non-null   int64  
 72  PoolQC         7 non-null      object 
 73  Fence          281 non-null    object 
 74  MiscFeature    54 non-null     object 
 75  MiscVal        1460 non-null   int64  
 76  MoSold         1460 non-null   int64  
 77  YrSold         1460 non-null   int64  
 78  SaleType       1460 non-null   object 
 79  SaleCondition  1460 non-null   object 
 80  SalePrice      1460 non-null   int64  
dtypes: float64(3), int64(35), object(43)
memory usage: 924.0+ KB

Columns

[Back to top]

df.dtypes

Id                 int64
MSSubClass         int64
MSZoning          object
LotFrontage      float64
LotArea            int64
                  ...   
MoSold             int64
YrSold             int64
SaleType          object
SaleCondition     object
SalePrice          int64
Length: 81, dtype: object

numerical_cols = [cname for cname in df.columns if df[cname].dtype in ['int64', 'float64']]
print('Number of numerical columns: ', len(numerical_cols))
# numerical_cols

Number of numerical columns:  38

categorical_columns = [cname for cname in df.columns if df[cname].dtype=='object']
print('Number of categorical columns: ', len(categorical_columns))
# categorical_columns

Number of categorical columns:  43

Missing Value Analysis

[Back to top]

msno.matrix(df)

png

cols_with_missing = [col for col in df.columns if df[col].isnull().any()]
print('Columns with missing values in df: ', cols_with_missing)

Columns with missing values in df:  ['LotFrontage', 'Alley', 'MasVnrType', 'MasVnrArea', 'BsmtQual', 'BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinType2', 'Electrical', 'FireplaceQu', 'GarageType', 'GarageYrBlt', 'GarageFinish', 'GarageQual', 'GarageCond', 'PoolQC', 'Fence', 'MiscFeature']

Handling Missing Values

[Back to top]

1. Omit Data

We filter out columns which contain more than 90% missing values.

nv1 = df.isnull().sum()
nv2 = nv1.where(nv1>0).dropna()/df.shape[0]*100
nv2.where(nv2>90).dropna()

Alley          93.767123
PoolQC         99.520548
MiscFeature    96.301370
dtype: float64

We see here PoolQC contains 99% missing values and we decide to go ahead and drop it.

cols_to_drop = ['PoolQC']

X = df.drop(cols_to_drop, axis=1)

if 'PoolQC' in X.columns:
    print('Drop Failed')
else:
    print('Drop Passed')

Drop Passed

2. Imputation

from sklearn.compose import ColumnTransformer
from sklearn.pipeline import Pipeline
from sklearn.impute import SimpleImputer
from sklearn.preprocessing import OneHotEncoder

# Preprocessing for numerical data
numerical_transformer = SimpleImputer(strategy='median')

# Preprocessing for categorical data
categorical_transformer = Pipeline(steps=[
    ('imputer', SimpleImputer(strategy='most_frequent')),
    ('onehot', OneHotEncoder(handle_unknown='ignore'))
])

# Bundle preprocessing for numerical and categorical data
preprocessor = ColumnTransformer(
    transformers=[
        ('num', numerical_transformer, numerical_cols),
        ('cat', categorical_transformer, categorical_columns)
    ])

Additional Notes on how to use these objects:

linear_reg_pipe = Pipeline(steps=[('preprocessor', preprocessor),('regressor', LinearRegression())])

linear_reg_pipe.fit(X_train, y_train)
linear_reg_preds = linear_reg_pipe.predict(X_test)

Unique Values

[Back to top]

df[categorical_columns].nunique()

MSZoning          5
Street            2
Alley             2
LotShape          4
LandContour       4
Utilities         2
LotConfig         5
LandSlope         3
Neighborhood     25
Condition1        9
Condition2        8
BldgType          5
HouseStyle        8
RoofStyle         6
RoofMatl          8
Exterior1st      15
Exterior2nd      16
MasVnrType        4
ExterQual         4
ExterCond         5
Foundation        6
BsmtQual          4
BsmtCond          4
BsmtExposure      4
BsmtFinType1      6
BsmtFinType2      6
Heating           6
HeatingQC         5
CentralAir        2
Electrical        5
KitchenQual       4
Functional        7
FireplaceQu       5
GarageType        6
GarageFinish      3
GarageQual        5
GarageCond        5
PavedDrive        3
PoolQC            3
Fence             4
MiscFeature       4
SaleType          9
SaleCondition     6
dtype: int64

Univariate Analysis

[Back to top]

fig, axes = plt.subplots(nrows=6, ncols=6, figsize=(30,30))
for i, col in enumerate(numerical_cols[0:-2]): 
    sns.distplot(df[col], kde=False, ax=axes[i//6,i%6])

png

fig, axes = plt.subplots(nrows=1, ncols=2, figsize=(15,5))
for i, col in enumerate(numerical_cols[36:]): 
    sns.distplot(df[col], kde=False, ax=axes[i])

png

Bivariate Distribution (Heatmap)

[Back to top]

plt.figure(figsize=(10,5))
sns.heatmap(df[numerical_cols].corr(), annot=False, cmap='coolwarm', fmt='.1f')

png

Web Scraping

[Back to top]

from bs4 import BeautifulSoup
import requests

res = requests.get("https://en.wikipedia.org/wiki/List_of_postal_codes_of_Canada:_M")
soup = BeautifulSoup(res.content,'lxml')
table = soup.find_all('table')[0]
df_can = pd.read_html(str(table))

df = df_can[0]

df.columns = df.iloc[0]
df = df[1:]

df.head()
M1A Not assigned Not assigned
1 M2A Not assigned Not assigned
2 M3A North York Parkwoods
3 M4A North York Victoria Village
4 M5A Downtown Toronto Regent Park, Harbourfront
5 M6A North York Lawrence Manor, Lawrence Heights