Kaggle——First Machine Learning Model

kaggle（需要魔法才能访问）:https://www.kaggle.com/
需要下载的数据集：melb_data.csv、train.csv（已放在资源里面）

First Machine Learning Model
Selecting Data for Modeling

#Selecting Data for Modeling
import pandas as pd
melbourne_file_path=r"G:\Kaggle\Datasets\archive\melb_data.csv"
melbourne_data=pd.read_csv(melbourne_file_path)
#查看数据集中所有列的列表,这是通过 DataFrame 的 columns 属性完成的
melbourne_data.columns

# dropna drops missing values (think of na as "not available")
#dropna 删除缺失值（将 na 视为“不可用”）
melbourne_data = melbourne_data.dropna(axis=0)

#Selecting The Prediction Target
#选择我们想要预测的列，这称为预测目标y
y=melbourne_data.Price

#Choosing "Features"
#输入到模型中（随后用于进行预测）的列称为“特征”
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'Lattitude', 'Longtitude']

#X
X = melbourne_data[melbourne_features]

#describe方法
X.describe()

	Rooms	Bathroom	Landsize	Lattitude	Longtitude
count	6196.000000	6196.000000	6196.000000	6196.000000	6196.000000
mean	2.931407	1.576340	471.006940	-37.807904	144.990201
std	0.971079	0.711362	897.449881	0.075850	0.099165
min	1.000000	1.000000	0.000000	-38.164920	144.542370
25%	2.000000	1.000000	152.000000	-37.855438	144.926198
50%	3.000000	1.000000	373.000000	-37.802250	144.995800
75%	4.000000	2.000000	628.000000	-37.758200	145.052700
max	8.000000	8.000000	37000.000000	-37.457090	145.526350

#head()方法
X.head()

	Rooms	Bathroom	Landsize	Lattitude	Longtitude
1	2	1.0	156.0	-37.8079	144.9934
2	3	2.0	134.0	-37.8093	144.9944
4	4	1.0	120.0	-37.8072	144.9941
6	3	2.0	245.0	-37.8024	144.9993
7	2	1.0	256.0	-37.8060	144.9954

Building Your Model

#Building Your Model
# 构建和使用模型的步骤是：
# 定义
# 拟合
# 预测
# 评估
from sklearn.tree import DecisionTreeRegressor
#定义模型
melbourne_model=DecisionTreeRegressor(random_state=1)
#拟合
melbourne_model.fit(X,y)

DecisionTreeRegressor(random_state=1)

In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook.
On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.

DecisionTreeRegressor

DecisionTreeRegressor(random_state=1)

print("Making predictions for the following 5 houses:")
print(X.head())
print("The predictions are")
print(melbourne_model.predict(X.head()))

Making predictions for the following 5 houses:Rooms  Bathroom  Landsize  Lattitude  Longtitude
1      2       1.0     156.0   -37.8079    144.9934
2      3       2.0     134.0   -37.8093    144.9944
4      4       1.0     120.0   -37.8072    144.9941
6      3       2.0     245.0   -37.8024    144.9993
7      2       1.0     256.0   -37.8060    144.9954
The predictions are
[1035000. 1465000. 1600000. 1876000. 1636000.]

Exercise First Machine Learning Model

#Exercise: First Machine Learning Model Exercises
import pandas as pd
iowa_file_path = r"G:\Kaggle\Datasets\archive\train.csv"
home_data = pd.read_csv(iowa_file_path)
#Step 1: Specify Prediction Target
print(home_data.columns)
y = home_data.SalePrice
#Step 2: Create X
feature_names = ["LotArea","YearBuilt","1stFlrSF","2ndFlrSF","FullBath","BedroomAbvGr","TotRmsAbvGrd"]
X=home_data[feature_names]
#Review Data在构建模型之前，快速浏览一下 X 以验证它看起来是否合理
print(X.describe())
print(X.head())
#Step 3: Specify and Fit Model
from sklearn.tree import DecisionTreeRegressor
#specify the model
iowa_model = DecisionTreeRegressor(random_state=1)
# Fit the model
iowa_model.fit(X,y)
#Step 4: Make Predictions
predictions = iowa_model.predict(X)
print(predictions)

Index(['Id', 'MSSubClass', 'MSZoning', 'LotFrontage', 'LotArea', 'Street','Alley', 'LotShape', 'LandContour', 'Utilities', 'LotConfig','LandSlope', 'Neighborhood', 'Condition1', 'Condition2', 'BldgType','HouseStyle', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd','RoofStyle', 'RoofMatl', 'Exterior1st', 'Exterior2nd', 'MasVnrType','MasVnrArea', 'ExterQual', 'ExterCond', 'Foundation', 'BsmtQual','BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinSF1','BsmtFinType2', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', 'Heating','HeatingQC', 'CentralAir', 'Electrical', '1stFlrSF', '2ndFlrSF','LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath','HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'KitchenQual','TotRmsAbvGrd', 'Functional', 'Fireplaces', 'FireplaceQu', 'GarageType','GarageYrBlt', 'GarageFinish', 'GarageCars', 'GarageArea', 'GarageQual','GarageCond', 'PavedDrive', 'WoodDeckSF', 'OpenPorchSF','EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'PoolQC','Fence', 'MiscFeature', 'MiscVal', 'MoSold', 'YrSold', 'SaleType','SaleCondition', 'SalePrice'],dtype='object')LotArea    YearBuilt     1stFlrSF     2ndFlrSF     FullBath  \
count    1460.000000  1460.000000  1460.000000  1460.000000  1460.000000   
mean    10516.828082  1971.267808  1162.626712   346.992466     1.565068   
std      9981.264932    30.202904   386.587738   436.528436     0.550916   
min      1300.000000  1872.000000   334.000000     0.000000     0.000000   
25%      7553.500000  1954.000000   882.000000     0.000000     1.000000   
50%      9478.500000  1973.000000  1087.000000     0.000000     2.000000   
75%     11601.500000  2000.000000  1391.250000   728.000000     2.000000   
max    215245.000000  2010.000000  4692.000000  2065.000000     3.000000   BedroomAbvGr  TotRmsAbvGrd  
count   1460.000000   1460.000000  
mean       2.866438      6.517808  
std        0.815778      1.625393  
min        0.000000      2.000000  
25%        2.000000      5.000000  
50%        3.000000      6.000000  
75%        3.000000      7.000000  
max        8.000000     14.000000  LotArea  YearBuilt  1stFlrSF  2ndFlrSF  FullBath  BedroomAbvGr  \
0     8450       2003       856       854         2             3   
1     9600       1976      1262         0         2             3   
2    11250       2001       920       866         2             3   
3     9550       1915       961       756         1             3   
4    14260       2000      1145      1053         2             4   TotRmsAbvGrd  
0             8  
1             6  
2             6  
3             7  
4             9  
[208500. 181500. 223500. ... 266500. 142125. 147500.]

#Exercise: First Machine Learning Model
#Step 1: Specify Prediction Target
print(home_data.columns)
y = home_data.SalePrice

Index(['Id', 'MSSubClass', 'MSZoning', 'LotFrontage', 'LotArea', 'Street','Alley', 'LotShape', 'LandContour', 'Utilities', 'LotConfig','LandSlope', 'Neighborhood', 'Condition1', 'Condition2', 'BldgType','HouseStyle', 'OverallQual', 'OverallCond', 'YearBuilt', 'YearRemodAdd','RoofStyle', 'RoofMatl', 'Exterior1st', 'Exterior2nd', 'MasVnrType','MasVnrArea', 'ExterQual', 'ExterCond', 'Foundation', 'BsmtQual','BsmtCond', 'BsmtExposure', 'BsmtFinType1', 'BsmtFinSF1','BsmtFinType2', 'BsmtFinSF2', 'BsmtUnfSF', 'TotalBsmtSF', 'Heating','HeatingQC', 'CentralAir', 'Electrical', '1stFlrSF', '2ndFlrSF','LowQualFinSF', 'GrLivArea', 'BsmtFullBath', 'BsmtHalfBath', 'FullBath','HalfBath', 'BedroomAbvGr', 'KitchenAbvGr', 'KitchenQual','TotRmsAbvGrd', 'Functional', 'Fireplaces', 'FireplaceQu', 'GarageType','GarageYrBlt', 'GarageFinish', 'GarageCars', 'GarageArea', 'GarageQual','GarageCond', 'PavedDrive', 'WoodDeckSF', 'OpenPorchSF','EnclosedPorch', '3SsnPorch', 'ScreenPorch', 'PoolArea', 'PoolQC','Fence', 'MiscFeature', 'MiscVal', 'MoSold', 'YrSold', 'SaleType','SaleCondition', 'SalePrice'],dtype='object')

#Step 2: Create X
feature_names = ["LotArea","YearBuilt","1stFlrSF","2ndFlrSF","FullBath","BedroomAbvGr","TotRmsAbvGrd"]
X=home_data[feature_names]
#Review Data在构建模型之前，快速浏览一下 X 以验证它看起来是否合理
print(X.describe())
print(X.head())

             LotArea    YearBuilt     1stFlrSF     2ndFlrSF     FullBath  \
count    1460.000000  1460.000000  1460.000000  1460.000000  1460.000000   
mean    10516.828082  1971.267808  1162.626712   346.992466     1.565068   
std      9981.264932    30.202904   386.587738   436.528436     0.550916   
min      1300.000000  1872.000000   334.000000     0.000000     0.000000   
25%      7553.500000  1954.000000   882.000000     0.000000     1.000000   
50%      9478.500000  1973.000000  1087.000000     0.000000     2.000000   
75%     11601.500000  2000.000000  1391.250000   728.000000     2.000000   
max    215245.000000  2010.000000  4692.000000  2065.000000     3.000000   BedroomAbvGr  TotRmsAbvGrd  
count   1460.000000   1460.000000  
mean       2.866438      6.517808  
std        0.815778      1.625393  
min        0.000000      2.000000  
25%        2.000000      5.000000  
50%        3.000000      6.000000  
75%        3.000000      7.000000  
max        8.000000     14.000000  LotArea  YearBuilt  1stFlrSF  2ndFlrSF  FullBath  BedroomAbvGr  \
0     8450       2003       856       854         2             3   
1     9600       1976      1262         0         2             3   
2    11250       2001       920       866         2             3   
3     9550       1915       961       756         1             3   
4    14260       2000      1145      1053         2             4   TotRmsAbvGrd  
0             8  
1             6  
2             6  
3             7  
4             9

#Step 3: Specify and Fit Model
from sklearn.tree import DecisionTreeRegressor
#specify the model
iowa_model = DecisionTreeRegressor(random_state=1)
# Fit the model
iowa_model.fit(X,y)

DecisionTreeRegressor(random_state=1)

DecisionTreeRegressor

DecisionTreeRegressor(random_state=1)

#Step 4: Make Predictions
predictions = iowa_model.predict(X)
print(predictions)

[208500. 181500. 223500. ... 266500. 142125. 147500.]

Model Validation 模型验证

# Model Validation 模型验证
import pandas as pd
# load data加载数据
melbourne_file_path = r"G:\Kaggle\Datasets\archive\melb_data.csv"
melbourne_data = pd.read_csv(melbourne_file_path) 
# Filter rows with missing price values过滤缺少价格值的行
filtered_melbourne_data = melbourne_data.dropna(axis=0)
# Choose target and features选择目标和特征
y = filtered_melbourne_data.Price
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'BuildingArea', 'YearBuilt', 'Lattitude', 'Longtitude']
X = filtered_melbourne_data[melbourne_features]
#模型的选择
from sklearn.tree import DecisionTreeRegressor
# Define model
melbourne_model = DecisionTreeRegressor()
# Fit model
melbourne_model.fit(X, y)

DecisionTreeRegressor()

DecisionTreeRegressor

DecisionTreeRegressor()

#calculate the mean absolute error计算平均绝对误差
from sklearn.metrics import mean_absolute_error
predicted_home_prices = melbourne_model.predict(X)
mean_absolute_error(y, predicted_home_prices)

434.71594577146544

#scikit-learn 库有一个函数 train_test_split 将数据分成两部分
#我们将使用其中一些数据作为训练数据来拟合模型，并使用其他数据作为验证数据来计算mean_absolute_error
from sklearn.model_selection import train_test_split
train_X, val_X, train_y, val_y = train_test_split(X, y, random_state = 0)
# Define model
melbourne_model = DecisionTreeRegressor()
# Fit model
melbourne_model.fit(train_X, train_y)
# get predicted prices on validation data根据验证数据获取预测价格
val_predictions = melbourne_model.predict(val_X)
print(mean_absolute_error(val_y, val_predictions))

263704.735958683

Exercise: Model Validation

#Exercise: Model Validation
import pandas as pd
from sklearn.tree import DecisionTreeRegressor# Path of the file to read
iowa_file_path = r"G:\Kaggle\Datasets\archive\train.csv"home_data = pd.read_csv(iowa_file_path)
y = home_data.SalePrice
feature_columns = ['LotArea', 'YearBuilt', '1stFlrSF', '2ndFlrSF', 'FullBath', 'BedroomAbvGr', 'TotRmsAbvGrd']
X = home_data[feature_columns]# Specify Model
iowa_model = DecisionTreeRegressor()
# Fit Model
iowa_model.fit(X, y)print("First in-sample predictions:", iowa_model.predict(X.head()))
print("Actual target values for those homes:", y.head().tolist())

First in-sample predictions: [208500. 181500. 223500. 140000. 250000.]
Actual target values for those homes: [208500, 181500, 223500, 140000, 250000]

#Exercise: Model Validation
#Step 1: Split Your Data
from sklearn.model_selection import train_test_split
train_X, val_X, train_y, val_y = train_test_split(X,y,random_state=1)

#Step 2: Specify and Fit the Model
# Specify the model
iowa_model = DecisionTreeRegressor(random_state=1)
# Fit iowa_model with the training data.
iowa_model.fit(train_X,train_y)

DecisionTreeRegressor(random_state=1)

DecisionTreeRegressor

DecisionTreeRegressor(random_state=1)

#Step 3: Make Predictions with Validation data使用验证数据进行预测
# Predict with all validation observations
val_predictions = iowa_model.predict(val_X)

# print the top few validation predictions
print(val_X.head())
# print the top few actual prices from validation data
print(val_y.head())

      LotArea  YearBuilt  1stFlrSF  2ndFlrSF  FullBath  BedroomAbvGr  \
258     12435       2001       963       829         2             3   
267      8400       1939      1052       720         2             4   
288      9819       1967       900         0         1             3   
649      1936       1970       630         0         1             1   
1233    12160       1959      1188         0         1             3   TotRmsAbvGrd  
258              7  
267              8  
288              5  
649              3  
1233             6  
258     231500
267     179500
288     122000
649      84500
1233    142000
Name: SalePrice, dtype: int64

#Step 4: Calculate the Mean Absolute Error in Validation Data
#步骤 4：计算验证数据中的平均绝对误差
from sklearn.metrics import mean_absolute_error
val_mae = mean_absolute_error(val_y,val_predictions)
#print(val_mae)

29652.931506849316

Underfitting and Overfitting

#Underfitting and Overfitting
#欠拟合和过拟合
from sklearn.metrics import mean_absolute_error
from sklearn.tree import DecisionTreeRegressordef 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)

import pandas as pd  
# Load data
melbourne_file_path = r"G:\Kaggle\Datasets\archive\melb_data.csv"
melbourne_data = pd.read_csv(melbourne_file_path) 
# Filter rows with missing values
filtered_melbourne_data = melbourne_data.dropna(axis=0)
# Choose target and features
y = filtered_melbourne_data.Price
melbourne_features = ['Rooms', 'Bathroom', 'Landsize', 'BuildingArea', 'YearBuilt', 'Lattitude', 'Longtitude']
X = filtered_melbourne_data[melbourne_features]from sklearn.model_selection import train_test_split# split data into training and validation data, for both features and target
train_X, val_X, train_y, val_y = train_test_split(X, y,random_state = 0)

# compare MAE with differing values of max_leaf_nodes
#将 MAE 与 max_leaf_nodes 的不同值进行比较
for max_leaf_nodes in [5, 50, 500, 5000]:my_mae = get_mae(max_leaf_nodes, train_X, val_X, train_y, val_y)print("Max leaf nodes: %d  \t\t Mean Absolute Error:  %d" %(max_leaf_nodes, my_mae))

Max leaf nodes: 5  		 Mean Absolute Error:  347380
Max leaf nodes: 50  		 Mean Absolute Error:  258171
Max leaf nodes: 500  		 Mean Absolute Error:  243495
Max leaf nodes: 5000  		 Mean Absolute Error:  255575

#之前用于加载数据的代码
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 = r"G:\Kaggle\Datasets\archive\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))

Validation MAE: 29,653

Exercise: Underfitting and Overfitting

#Exercise: Underfitting and Overfitting
#Exercises
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)

#Step 1: Compare Different Tree Sizes
candidate_max_leaf_nodes = [5, 25, 50, 100, 250, 500]
# Write loop to find the ideal tree size from candidate_max_leaf_nodes
for leaf_size in candidate_max_leaf_nodes:leaf_size = get_mae(leaf_size, train_X, val_X, train_y, val_y)# Store the best value of max_leaf_nodes (it will be either 5, 25, 50, 100, 250 or 500)
best_tree_size = min(scores, key=scores.get)

#Step 2: Fit Model Using All Data
# Fill in argument to make optimal size and uncomment
final_model = DecisionTreeRegressor(max_leaf_nodes=best_tree_size,random_state=1)
# fit the final model and uncomment the next two lines
final_model.fit(X,y)