/
app.py
147 lines (115 loc) · 3.96 KB
/
app.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
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
import pandas as pd
from pandas import DataFrame,Series
import numpy as np
from sklearn import linear_model,neighbors , svm ,tree,ensemble
import matplotlib
import matplotlib.pyplot as plt
matplotlib.rcParams['figure.figsize'] = (6.0, 6.0)
def ridge_regression(x_train, y_train, x_test):
model = linear_model.Ridge()
model.fit(x_train, y_train)
return model.predict(x_test)
def simple_linear_regression(x_train, y_train, x_test):
model = linear_model.LinearRegression()
model.fit(x_train, y_train)
return model.predict(x_test)
def knn_regression(x_train,y_train,x_test):
model=neighbors.KNeighborsRegressor(10,weights='uniform')
model.fit(x_train,y_train)
return model.predict(x_test)
def lasso(x_train,y_train,x_test):
model = linear_model.Lasso(alpha=0.1)
model.fit(x_train,y_train)
return model.predict(x_test)
def bayesian_regression(x_train,y_train,x_test):
model=linear_model.BayesianRidge()
model.fit(x_train,y_train)
return model.predict(x_test)
def suppor_vector_machine(x_train,y_train,x_test):
model = svm.SVR()
model.fit(x_train,y_train)
return model.predict(x_test)
def decision_tree(x_train,y_train,x_test):
model = tree.DecisionTreeRegressor(max_depth=7)
model.fit(x_train,y_train)
return model.predict(x_test)
def random_forest(x_train,y_train,x_test):
model = ensemble.RandomForestRegressor(n_estimators=10)
model.fit(x_train,y_train)
return model.predict(x_test)
def calc_error(y_test, y_predict):
err = 0
s = 0
for y, yp in zip(y_test, y_predict) :
s += abs(y - yp)
err += (y - yp) ** 2
print("MSE:")
print(err / len(x_test))
print("Average error:")
print(s / len(x_test))
def residual_plot(y_test,y_predict):
preds = pd.DataFrame({"preds":y_predict, "true":y_test})
preds["residuals"] = preds["true"] - preds["preds"]
preds.plot(x = "preds", y = "residuals",kind = "scatter")
plt.title("Residual plot")
plt.show()
if __name__ == "__main__":
f = pd.read_csv("movie_metadata.csv")
data=DataFrame(f)
cols=data.dtypes[data.dtypes!='object'].index
#cols=['duration','num_voted_users','imdb_score']
x=data[cols]
x=x.fillna(0)
y=x['imdb_score']
x.drop(['imdb_score'],axis=1,inplace=True)
x=x.values
y=np.asarray(y)
x=np.asarray(x)
number_of_samples = len(y)
np.random.seed(15)
random_indices = np.random.permutation(number_of_samples)
num_training_samples = int(number_of_samples*0.75)
x_train = x[random_indices[:num_training_samples]]
y_train=y[random_indices[:num_training_samples]]
x_test=x[random_indices[num_training_samples:]]
y_test=y[random_indices[num_training_samples:]]
choice = -1
while True:
choice = int(input("\nChoose an algorithm: \n1.Simple Linear Regression\n2.KNN Regression\n"
+"3.Bayesian Regression.\n4.SVR\n5.Ridge Regression\n"
+"6.Decision Tree\n7.Lasso\n8.Random Forest\n"
+"0. exit\n"))
if choice == 1:
y_predict = simple_linear_regression(x_train, y_train, x_test)
calc_error(y_test, y_predict)
residual_plot(y_test, y_predict)
elif choice == 2:
y_predict = knn_regression(x_train,y_train,x_test)
calc_error(y_test,y_predict)
residual_plot(y_test,y_predict)
elif choice == 3:
y_predict= bayesian_regression(x_train,y_train,x_test)
calc_error(y_test,y_predict)
residual_plot(y_test,y_predict)
elif choice == 4:
y_predict=suppor_vector_machine(x_train,y_train,x_test)
calc_error(y_test,y_predict)
residual_plot(y_test,y_predict)
elif choice == 5:
y_predict = ridge_regression(x_train, y_train, x_test)
calc_error(y_test, y_predict)
residual_plot(y_test,y_predict)
elif choice == 6:
y_predict = decision_tree(x_train, y_train, x_test)
calc_error(y_test, y_predict)
residual_plot(y_test,y_predict)
elif choice == 7 :
y_predict = lasso(x_train, y_train, x_test)
calc_error(y_test, y_predict)
residual_plot(y_test,y_predict)
elif choice == 8 :
y_predict = random_forest(x_train, y_train, x_test)
calc_error(y_test, y_predict)
residual_plot(y_test,y_predict)
elif choice == 0:
break