-
Notifications
You must be signed in to change notification settings - Fork 0
/
machineLearning.py
114 lines (86 loc) · 3.58 KB
/
machineLearning.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
'''
import pandas as pd
iowa_file_path = '../input/home-data-for-ml-course/train.csv'
home_data = pd.read_csv(iowa_file_path)
home_data.columns # Print out list of columns in table
y = home_data['SalePrice']
# 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]
# Print 1st 5 rows or table
head = home_data.head()
print(head)
home_data.describe()
from sklearn.tree import DecisionTreeRegressor
#specify the model.
#For model reproducibility, set a numeric value for random_state when specifying the model
iowa_model = DecisionTreeRegressor(random_state=1)
iowa_model.fit(X, y)
predictions = iowa_model.predict(X)
print(predictions)
Model Validation
from sklearn.metrics import mean_absolute_error
predicted_home_prices = melbourne_model.predict(X)
mean_absolute_error(y, predicted_home_prices)
Need to split data into 2 tables. One table for training the model, the other for testing the accuracy of the predictions
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 = 0)
# Define model
melbourne_model = DecisionTreeRegressor()
# Fit model
melbourne_model.fit(train_X, train_y)
# get predicted prices on validation data
val_predictions = melbourne_model.predict(val_X)
print(mean_absolute_error(val_y, val_predictions))
'''
'''
Testing Overfitting and underfitting
from sklearn.metrics import mean_absolute_error
from sklearn.tree import DecisionTreeRegressor
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)
# compare MAE with differing values of max_leaf_nodes
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))
'''
'''
Summary
# 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))
After determining the best depth for tree
# 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)
'''