Housing Prices Competition

版权声明：本文为博主原创文章，未经博主允许不得转载。 https://blog.csdn.net/u013317445/article/details/84637131

# Code you have previously used to load data
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from sklearn.metrics import mean_absolute_error
from sklearn.model_selection import train_test_split
from sklearn.tree import DecisionTreeRegressor




# Path of the file to read. We changed the directory structure to simplify submitting to a competition
iowa_file_path = r'G:/kaggle/housePrice/train.csv'

home_data = pd.read_csv(iowa_file_path)
# Create target object and call it y
y = home_data.SalePrice
# Create X
features = ['LotArea','YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd', 
            'MSSubClass','OverallQual','OverallCond','YearRemodAdd','MasVnrArea','BsmtFullBath','BsmtHalfBath','HalfBath','KitchenAbvGr','TotRmsAbvGrd','Fireplaces','GarageCars','GarageArea','PoolArea']
X = home_data[features]

#handle NaN , mean values every column
from sklearn.impute import SimpleImputer
my_imputer = SimpleImputer()
X = my_imputer.fit_transform(X)

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

# Specify Model
iowa_model = DecisionTreeRegressor(random_state=1)
# Fit Model
iowa_model.fit(train_X, train_y)

# Make validation predictions and calculate mean absolute error
val_predictions = iowa_model.predict(val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE when not specifying max_leaf_nodes: {:,.0f}".format(val_mae))

# Using best value for max_leaf_nodes
iowa_model = DecisionTreeRegressor(max_leaf_nodes=100, random_state=1)
iowa_model.fit(train_X, train_y)
val_predictions = iowa_model.predict(val_X)
val_mae = mean_absolute_error(val_predictions, val_y)
print("Validation MAE for best value of max_leaf_nodes: {:,.0f}".format(val_mae))

# Define the model. Set random_state to 1
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))

Validation MAE when not specifying max_leaf_nodes: 28,365
Validation MAE for best value of max_leaf_nodes: 26,087
Validation MAE for Random Forest Model: 18,974


d:\python27\lib\site-packages\sklearn\ensemble\forest.py:248: FutureWarning: The default value of n_estimators will change from 10 in version 0.20 to 100 in 0.22.
  "10 in version 0.20 to 100 in 0.22.", FutureWarning)

Create a model :采用了Random Forest

# To improve accuracy, create a new Random Forest model which you will train on all training data
rf_model_on_full_data = RandomForestRegressor(random_state=1)

# fit rf_model_on_full_data on all data from the 
rf_model_on_full_data.fit(X,y)

RandomForestRegressor(bootstrap=True, criterion='mse', max_depth=None,
           max_features='auto', max_leaf_nodes=None,
           min_impurity_decrease=0.0, min_impurity_split=None,
           min_samples_leaf=1, min_samples_split=2,
           min_weight_fraction_leaf=0.0, n_estimators=10, n_jobs=None,
           oob_score=False, random_state=1, verbose=0, warm_start=False)

Make predictions

# path to file you will use for predictions
test_data_path = r'G:/kaggle/housePrice/test.csv'

# read test data file using pandas
test_data = pd.read_csv(test_data_path)

# create test_X which comes from test_data but includes only the columns you used for prediction.
# The list of columns is stored in a variable called features
test_X = test_data[features]

#handle NaN , mean values every column
from sklearn.impute import SimpleImputer
my_imputer = SimpleImputer()
test_X = my_imputer.fit_transform(test_X)

# make predictions which we will submit. 
test_preds = rf_model_on_full_data.predict(test_X)

# The lines below shows you how to save your data in the format needed to score it in the competition
output = pd.DataFrame({'Id': test_data.Id,
                       'SalePrice': test_preds})

output.to_csv(r'G:/kaggle/housePrice/submission.csv',index=0)

output.head()

	Id	SalePrice
0	1461	121550.8
1	1462	151415.0
2	1463	174114.0
3	1464	175490.0
4	1465	201250.0