Newer
Older
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
def dataload():
"""
upload toy datasets from scikit-learn
"""
data = None
return data
def datafetch(file_name):
"""
upload real world datasets from scikit-learn
"""
data = None
print("reading data from:", file_name)
return data
def descriptive_statistic(df):
"""
Provides brief descriptive statistics on dataset.
Takes dataframe as input.
"""
print("Type : ", None, "\n\n")
print("Shape : ", None)
print("Head -- \n", None)
print("\n\n Tail -- \n", None)
print("Describe : ", None)
def model_selection(df):
"""
Takes dateframe as input. Performs foward/backward stepwise
regression. Returns best model for both methods.
"""
null_fit = None
foward_step = None
backward_step = None
return foward_step, backward_step
def MSE_fit(fit):
"""
Takes in a fitted model as the input.
Calculates the MSU of the fitted model.
Outputs the model's MSE.
"""
MSE = None
return MSE
def accuracy_metrics(fit, MSE):
"""
This function is used for model validation. It returns a dictionary
of several regression model accuracy metrics. Its inputs are a fitted model
and the MSE of the fitted model.
"""
d = dict()
sumObj = None
SSE = None
n = None
p = None
pr = None
d['R2'] = None
d['R2ad'] = None
d['AIC'] = None
d['BIC'] = None
d['PRESS'] = None
d['Cp']= None
return d