-
Notifications
You must be signed in to change notification settings - Fork 0
/
Asian_joro_classifiers.py
145 lines (119 loc) · 6.48 KB
/
Asian_joro_classifiers.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
from numpy import *
import pandas as pd
from sklearn.model_selection import train_test_split
from sklearn.neighbors import KNeighborsClassifier
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn import tree
from sklearn import svm
from sklearn.linear_model import LogisticRegression
from sklearn.svm import SVC
from sklearn.naive_bayes import GaussianNB
import pickle
def loadData(filename):
observations = pd.read_csv(filename)
Y = observations.iloc[:, -1]
X = observations.iloc[:, 0:19]
X_train, X_test, Y_train, Y_test = train_test_split(X, Y, test_size=0.2, random_state=42)
return X_train, X_test, Y_train, Y_test
def classifier(clfname, clf, X_train, X_test, Y_train, Y_test, save_to=''):
print(clfname)
clf.fit(X_train, Y_train)
if save_to != "":
pickle.dump(clf, open(save_to, 'wb'))
Predict = (clf.predict(X_test))
target_names = ['class 0', 'class 1']
confusion_matrix(Y_test, Predict)
return(classification_report(Y_test, Predict, target_names = target_names))
"""
test_definition = {
'nearest_neighbor': {
'process': True,
'model': KNeighborsClassifier(n_neighbors=5, weights='distance')
},
'decision_tree': {
'process': True,
'model': tree.DecisionTreeClassifier(criterion='log_loss', max_features='sqrt')
},
'logistic_regression': {
'process': True,
'model': LogisticRegression(max_iter=35000, C=5, solver='liblinear')
},
'support_verctor': {
'process': True,
'model': svm.SVC(C=10, kernel='linear')
},
'naive_bayes': {
'process': True,
'model': GaussianNB()
}
}
test_data = {
'Balanced': "combined_joro_v2.csv",
'Imbalanced': "combined_joro_imbalanced.csv"
}
important_features = ['MeanDiurnalRange', 'Isothermality', 'TempAnnRange','MeanTempWetQtr', 'AnnPercip', 'PrecipWetQtr', 'PrecipWrmQtr']
for obs_name, file_name in test_data.items():
print(obs_name, file_name)
X_train, X_test, Y_train, Y_test = loadData(file_name)
for model_name, mp in test_definition.items():
if mp['process'] == False:
continue
print(classifier(model_name, mp['model'], X_train, X_test, Y_train, Y_test))
X_train = X_train[['MeanDiurnalRange', 'Isothermality', 'TempAnnRange','MeanTempWetQtr', 'AnnPercip', 'PrecipWetQtr', 'PrecipWrmQtr']]
X_test = X_test[['MeanDiurnalRange', 'Isothermality', 'TempAnnRange','MeanTempWetQtr', 'AnnPercip', 'PrecipWetQtr', 'PrecipWrmQtr']]
print(classifier(f"{model_name} w/importance", mp['model'], X_train, X_test, Y_train, Y_test))
## Taken from: https://machinelearningmastery.com/save-load-machine-learning-models-python-scikit-learn/
# Save the model
X_train, X_test, Y_train, Y_test = loadData('combined_joro_v2.csv')
print(classifier('decision tree', tree.DecisionTreeClassifier(), X_train, X_test, Y_train, Y_test, save_to="decision_tree_model.sav"))
# Load and test the model
loaded_model = pickle.load(open("decision_tree_model.sav", 'rb'))
result = loaded_model.score(X_test, Y_test)
print(result)
"""
X_train, X_test, Y_train, Y_test = loadData('combined_joro_v2.csv')
clf = tree.DecisionTreeClassifier()
clf.fit(X_train, Y_train)
Predict = (clf.predict(X_test))
target_names = ['class 0', 'class 1']
confusion_matrix(Y_test, Predict)
print(classification_report(Y_test, Predict, target_names = target_names))
import numpy as np
from sklearn import metrics
fpr, tpr, thresholds = metrics.roc_curve(Y_test, Predict)
print("AUC: {}".format(metrics.auc(fpr, tpr)))
"""
X_train, X_test, Y_train, Y_test = loadData('combined_joro_v2.csv')
print(classifier('kNN', KNeighborsClassifier(n_neighbors=5), X_train, X_test, Y_train, Y_test))
print(classifier('decision tree', tree.DecisionTreeClassifier(), X_train, X_test, Y_train, Y_test))
print(classifier('Logistic Regression', LogisticRegression(random_state=0, max_iter=35000), X_train, X_test, Y_train, Y_test))
print(classifier('SVC', SVC(), X_train, X_test, Y_train, Y_test))
print(classifier('Naive Bayes', GaussianNB(), X_train, X_test, Y_train, Y_test))
X_train, X_test, Y_train, Y_test = loadData('combined_joro_unbalanced.csv')
print(classifier('kNN', KNeighborsClassifier(n_neighbors=5), X_train, X_test, Y_train, Y_test))
print(classifier('decision tree', tree.DecisionTreeClassifier(), X_train, X_test, Y_train, Y_test))
print(classifier('Logistic Regression', LogisticRegression(random_state=0, max_iter=35000), X_train, X_test, Y_train, Y_test))
print(classifier('SVC', SVC(), X_train, X_test, Y_train, Y_test))
print(classifier('Naive Bayes', GaussianNB(), X_train, X_test, Y_train, Y_test))
print('Permutation Importance - Random Forest using permutation, values above 0.2')
X_train, X_test, Y_train, Y_test = loadData('combined_joro_v2.csv')
#X_train = X_train[['Annual_mean_temp', 'PrecipDryQtr', 'PercipSeasonality', 'MeanTempWetQtr', 'PercipDryMo']]
#X_test = X_test[['Annual_mean_temp', 'PrecipDryQtr', 'PercipSeasonality', 'MeanTempWetQtr', 'PercipDryMo']]
X_train = X_train[['MeanDiurnalRange', 'Isothermality', 'TempAnnRange','MeanTempWetQtr', 'AnnPercip', 'PrecipWetQtr', 'PrecipWrmQtr']]
X_test = X_test[['MeanDiurnalRange', 'Isothermality', 'TempAnnRange','MeanTempWetQtr', 'AnnPercip', 'PrecipWetQtr', 'PrecipWrmQtr']]
print(classifier('kNN', KNeighborsClassifier(n_neighbors=5), X_train, X_test, Y_train, Y_test))
print(classifier('decision tree', tree.DecisionTreeClassifier(), X_train, X_test, Y_train, Y_test))
print(classifier('Logistic Regression', LogisticRegression(random_state=0, max_iter=35000), X_train, X_test, Y_train, Y_test))
print(classifier('SVC', SVC(), X_train, X_test, Y_train, Y_test))
print(classifier('Naive Bayes', GaussianNB(), X_train, X_test, Y_train, Y_test))
print('Feature Importance - Chi-Squared')
X_train, X_test, Y_train, Y_test = loadData('combined_joro_v2.csv')
X_train = X_train[['Annual_mean_temp', 'PrecipDryQtr', 'PercipSeasonality', 'MeanTempWetQtr', 'PercipDryMo']]
X_test = X_test[['Annual_mean_temp', 'PrecipDryQtr', 'PercipSeasonality', 'MeanTempWetQtr', 'PercipDryMo']]
print(classifier('kNN', KNeighborsClassifier(n_neighbors=5), X_train, X_test, Y_train, Y_test))
print(classifier('decision tree', tree.DecisionTreeClassifier(), X_train, X_test, Y_train, Y_test))
print(classifier('Logistic Regression', LogisticRegression(random_state=0, max_iter=35000), X_train, X_test, Y_train, Y_test))
print(classifier('SVC', SVC(), X_train, X_test, Y_train, Y_test))
print(classifier('Naive Bayes', GaussianNB(), X_train, X_test, Y_train, Y_test))
"""