kaggle课程（二）Intro to Machine Learning

一、Your First Machine Learning Model

# Code you have previously used to load data
import pandas as pd

# 加载数据
iowa_file_path = '../input/home-data-for-ml-course/train.csv'

home_data = pd.read_csv(iowa_file_path)

#删除空值的行
home_data = home_data.dropna(axis=0)

#预览
home_data.columns

#选取目标预测值Specify Prediction Target
y = home_data.SalePrice

# 创建特征值Create the list of features below
feature_names = ['LotArea','YearBuilt','1stFlrSF','2ndFlrSF','FullBath','BedroomAbvGr','TotRmsAbvGrd']
# Select data corresponding to features in feature_names
X = home_data[feature_names]

# 预览Review data
# print description or statistics from X
print(X.describe())
# print the top few lines
print(X.head())

from sklearn.tree import DecisionTreeRegressor
#创建模型specify the model. 
#For model reproducibility, set a numeric value for random_state when specifying the model
iowa_model = DecisionTreeRegressor(random_state = 1)

# Fit the model
iowa_model.fit(X,y)

#Make Predictions
predictions = iowa_model.predict(X)
print(predictions)
print("Making predictions for the following 5 houses:")
print(X.head())
print("The predictions are")
print(melbourne_model.predict(X.head()))

二、Model Validation

首先我们需要区分验证集和训练集

from sklearn.model_selection import train_test_split

# split data into training and validation data, for both features and target
# The split is based on a random number generator. Supplying a numeric value to
# the random_state argument guarantees we get the same split every time we
# run this script.
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state = 1)
# Define model
melbourne_model = DecisionTreeRegressor(random_state=1)
# Fit model
melbourne_model.fit(train_X, train_y)

然后使用验证集进行预测：

# Predict with all validation observations
val_predictions = iowa_model.predict(val_X)
# print the top few validation predictions
print(val_predictions[:5])
# print the top few actual prices from validation data
print(val_y[:5])

最后打印MAE的值：

from sklearn.metrics import mean_absolute_error
val_mae = mean_absolute_error(val_y,val_predictions)

# uncomment following line to see the validation_mae
print(val_mae)

三、Underfitting and Overfitting

# Code you have previously used to load data
import pandas as pd
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
iowa_file_path = '../input/home-data-for-ml-course/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']
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)

# 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: {:,.0f}".format(val_mae))

选取最合适的值：

def get_mae(max_leaf_nodes, train_X, val_X, train_y, val_y):
    model = DecisionTreeRegressor(max_leaf_nodes=max_leaf_nodes, random_state=0)
    model.fit(train_X, train_y)
    preds_val = model.predict(val_X)
    mae = mean_absolute_error(val_y, preds_val)
    return(mae)

candidate_max_leaf_nodes = [5, 25, 50, 100, 250, 500]
# Write loop to find the ideal tree size from candidate_max_leaf_nodes
scores = {leaf_size: get_mae(leaf_size, train_X, val_X, train_y, val_y) for leaf_size in candidate_max_leaf_nodes}
best_tree_size = min(scores, key=scores.get)

建造最终模型

# Fit the model with best_tree_size. Fill in argument to make optimal size
final_model = DecisionTreeRegressor(max_leaf_nodes=best_tree_size, random_state=1)

# fit the final model
final_model.fit(X, y)

四、Random Forests

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
iowa_file_path = '../input/home-data-for-ml-course/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']
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 the model. Set random_state to 1
rf_model = RandomForestRegressor(random_state = 1)

# fit your model
rf_model.fit(train_X,train_y)

# Calculate the mean absolute error of your Random Forest model on the validation data
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: {}".format(rf_val_mae))