ML - Nano Desafio 2 - Duplicate

import pandas as pd housing = pd.read_csv('/work/data/train.csv') housing.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

housing.describe()

Idfloat64

MSSubClassfloat64

count

1460

mean

730.5

56.89726027

std

421.6100094

42.30057099

min

25%

365.75

50%

730.5

75%

1095.25

max

1460

190

housing.head()

Idint64

MSSubClassint64

housing.FireplaceQu.fillna('NA',inplace=True) housing.FireplaceQu.value_counts()

housing = housing.drop(['Alley','PoolQC','Fence','MiscFeature'], axis=1) housing = housing.dropna(axis=0)

def select_cols_corr(df_corr, target_col, min_corr, max_corr): #creating df target_corr target_corr = df_corr[target_col].reset_index() return target_corr.loc[(target_corr.iloc[:,1] < max_corr) & (target_corr.iloc[:,1] > min_corr),:] select_cols_corr(housing.corr(), 'SalePrice', min_corr=.4, max_corr=.95)

indexobject

OverallQual8.3%

YearBuilt8.3%

10 others83.3%

SalePricefloat64

0.4730731635797986 - 0.7763293256883151

OverallQual

0.7763293257

YearBuilt

0.4730731636

YearRemodAdd

0.5197465658

MasVnrArea

0.4810886371

TotalBsmtSF

0.5749262195

1stFlrSF

0.5609026401

GrLivArea

0.6622890383

FullBath

0.5086736733

TotRmsAbvGrd

0.5472253411

GarageYrBlt

0.4880180727

from sklearn.preprocessing import OneHotEncoder encoder = OneHotEncoder(sparse=False) categorical_var = ['Electrical','CentralAir', 'HeatingQC', 'Heating','BsmtFinType2', 'BsmtFinType1', 'BsmtExposure','BsmtCond','BsmtQual','Foundation','ExterCond','ExterQual','MasVnrType', 'Exterior2nd', 'Exterior1st', 'RoofMatl','RoofStyle', 'HouseStyle','BldgType', 'Condition2', 'Condition1', 'Neighborhood', 'LandSlope', 'LotConfig', 'Utilities', 'LandContour', 'LotShape', 'Street','MSZoning','KitchenQual','Functional','FireplaceQu', 'GarageType', 'GarageFinish', 'GarageQual','GarageCond','PavedDrive', 'SaleType','SaleCondition'] train_X_encoded = pd.DataFrame(encoder.fit_transform(housing[categorical_var])) train_X_encoded.columns = encoder.get_feature_names_out()

train_X_encoded.head()

Electrical_FuseAfloat64

Electrical_FuseFfloat64

housing = pd.concat([housing,train_X_encoded],axis=1)

housing.head()

Idfloat64

MSSubClassfloat64

nan

Sem as variáveis categóricas

x_treino = housing[['OverallQual','YearBuilt','YearRemodAdd','FullBath','Fireplaces', 'MasVnrArea','TotalBsmtSF','1stFlrSF','GrLivArea','TotRmsAbvGrd']] y_treino = housing['SalePrice']

import numpy as np from sklearn.ensemble import RandomForestRegressor from sklearn.model_selection import cross_val_score rs_model = RandomForestRegressor(random_state=1) scores_rs_model = cross_val_score(rs_model,x_treino,y_treino,cv=10) print(np.mean(scores_rs_model))

0.7856668365404486

Com as variáveis categóricas

variaveis = ['OverallQual','YearBuilt','YearRemodAdd','FullBath','Fireplaces', 'MasVnrArea','TotalBsmtSF','1stFlrSF','GrLivArea','TotRmsAbvGrd']+list(train_X_encoded.columns)

variaveis

housing.dropna(axis=0,inplace=True) x_treino2 = housing[variaveis] y_treino2 = housing['SalePrice']

x_treino2.isnull().sum()

rs_model2 = RandomForestRegressor(random_state=1) scores_rs_model2 = cross_val_score(rs_model2,x_treino2,y_treino2,cv=5) print(np.mean(scores_rs_model2))

0.7509831598656218

.css-ytumd6{-webkit-text-decoration:none;text-decoration:none;}Sem as variáveis categóricas

Com as variáveis categóricas

Sem as variáveis categóricas