# Kaggle Challenge 12 - Missing Values

ljsk99499·2021년 8월 14일
0 # Kaggle Challenge 12 - Missing Values

### 1. Housing Prices Competition

#### 1) Setup

import os
if not os.path.exists("../input/train.csv"):
from learntools.core import binder
binder.bind(globals())
from learntools.ml_intermediate.ex2 import *
print("Setup Complete")

#### 2) Pandas

# Import helpful libraries
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split

# Load the data, and separate the target
iowa_file_path = '../input/train.csv'
y = home_data.SalePrice

# Create X (After completing the exercise, you can return to modify this line!)
features = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd']

# Select columns corresponding to features, and preview the data
X = home_data[features]

# Split into validation and training data
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state=1)

# Define a random forest model
rf_model = RandomForestRegressor(random_state=1)
rf_model.fit(train_X, train_y)
rf_val_predictions = rf_model.predict(val_X)
rf_val_mae = mean_absolute_error(rf_val_predictions, val_y)

print("Validation MAE for Random Forest Model: {:,.0f}".format(rf_val_mae))

#### Step 1: Preliminary investigation

# Shape of training data (num_rows, num_columns)
print(X_train.shape)

# Number of missing values in each column of training data
missing_val_count_by_column = (X_train.isnull().sum())
print(missing_val_count_by_column[missing_val_count_by_column > 0])

#### 4) Solution

Solution:

# How many rows are in the training data?
num_rows = 1168

# How many columns in the training data have missing values?
num_cols_with_missing = 3

# How many missing entries are contained in all of the training data?
tot_missing = 212 + 6 + 58