-
Notifications
You must be signed in to change notification settings - Fork 1
/
nb.py
174 lines (135 loc) · 6.06 KB
/
nb.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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
from os.path import dirname, join
import numpy as np
import pandas as pd
import pandas.io.sql as psql
import sqlite3 as sql
from io import StringIO
from bokeh.plotting import figure
from bokeh.layouts import layout, widgetbox, row
from bokeh.models import ColumnDataSource, HoverTool, Div, LabelSet, Slider, Panel, Tabs, Range1d
from bokeh.models.widgets import MultiSelect, TextInput, Select, Button, Paragraph
from bokeh.io import curdoc
from sklearn import svm
from sklearn.model_selection import train_test_split
from sklearn.metrics import classification_report, confusion_matrix
from sklearn.metrics import accuracy_score, precision_recall_curve, average_precision_score
from bokeh.transform import factor_cmap
from bokeh.palettes import Spectral6
from sklearn.feature_selection import SelectKBest
from sklearn.feature_selection import chi2
from sklearn.feature_selection import SelectFromModel
from sklearn.naive_bayes import GaussianNB
args = curdoc().session_context.request.arguments
datasetname = str(args.get('dsname')[0].decode('utf-8'))
#datasetname = "churn.csv"
print("Dataset name is " +datasetname)
desc = Div(text="""
<h2 style="font-family="Arial">
Select the features to be included in the Naive Bayes Model
</h2>
<p><a href="http://scikit-learn.org/stable/modules/generated/sklearn.naive_bayes.GaussianNB.html#sklearn.naive_bayes.GaussianNB" target="_blank">Click here </a>for more information on the parameters </p>
""",width=1100)
#obj = client.get_object(Bucket='my-bucket', Key='churn.csv')
#df = pd.read_csv(obj['Body'])
#df = pd.read_csv('/Users/adilkhan/Documents/CS Fall 16/CS297/Bokeh-Demo/EmbedWebsite/cancer.csv')
df = pd.read_csv(datasetname)
y = df[df.columns[:1]].values.ravel()
df1 = df.drop(df.columns[:1],axis=1)
features = MultiSelect(title="Features",
options=df.columns[1:].tolist())
target = Paragraph(text='',name = 'target')
target.text = "Target feature is " + str(df.columns[:1].tolist())
stats = Paragraph(text='',width=1000,name = 'Selected Features:')
y = df[df.columns[:1]].values.ravel()
df1 = df.drop(df.columns[:1],axis=1)
selector = SelectKBest(chi2, k=5).fit(df1, y)
X_new = selector.transform(df1)
mask = selector.get_support() #list of booleans
new_features = [] # The list of your K best features
for bool, feature in zip(mask, df.columns[1:].tolist()):
if bool:
new_features.append(feature)
#print(new_features)
features.value = new_features
stats.text = str(new_features)
x_train_original,x_test_original,y_train_original,y_test_original=train_test_split(X_new,y,test_size=0.25)
#For standardizing data
#clf = svm.LinearSVC(random_state=0)
clf = GaussianNB()
clf.fit(x_train_original,y_train_original)
predictions=clf.predict(x_test_original)
#print("Accuracy =", accuracy_score(y_test_original,predictions))
#print(np.unique(predictions))
tn, fp, fn, tp = confusion_matrix(y_test_original,predictions).ravel()
fruits = ['True Positive', 'False Positive', 'True Negative', 'False Negative']
#fruits = [tp, fp, tn, fn]
#counts = [0, 0, 0, 0]
counts = [tp, fp, tn, fn]
source = ColumnDataSource(data=dict(fruits=fruits, counts=counts))
p = figure(x_range=fruits, plot_height=350, title="Counts")
p.vbar(x='fruits', top='counts', width=0.9, source=source, legend="fruits",
line_color='white',fill_color=factor_cmap('fruits', palette=Spectral6, factors=fruits))
p.title.text = "Model Accuracy %f" % accuracy_score(y_test_original,predictions)
labels = LabelSet(x='fruits', y='counts', text='counts', level='glyph',
x_offset=-15, y_offset=0, source=source, render_mode='canvas')
p.yaxis.axis_label = "Counts"
p.add_layout(labels)
tab1 = Panel(child=p, title="Accuracy Scores")
p1 = figure(plot_height=350, title="PR Curve")
p1.x_range = Range1d(0,1)
p1.y_range = Range1d(0,1)
p1.yaxis.axis_label = "Precision"
p1.xaxis.axis_label = "Recall"
#p1.line([0],[0],name ="line2")
y_score = clf.predict_proba(x_test_original)[:,1]
precision, recall, _ = precision_recall_curve(y_test_original, y_score)
p.yaxis.axis_label = "Counts"
#fpr,tpr, _ = roc_curve(y_test_original, predictions)
#print(fpr)
#print(tpr)
p1.line(precision, recall, line_width=2,line_alpha=0.6,name ="line2")
average_precision = average_precision_score(y_test_original, predictions)
p1.title.text = "Average Precision Score %f" % average_precision
tab2 = Panel(child=p1, title="PR Curve")
tabs = Tabs(tabs=[ tab1, tab2 ])
#p.title.text = "Model Accuracy %f" % accuracy_score(y_test_original,predictions)
def update():
line = p1.select_one({'name': 'line2'})
p1.renderers.remove(line)
line.visible = False
precision = 0
recall = 0
p1.line(precision,recall,line_alpha=0)
fval = features.value
print(fval)
stats.text = str(fval)
df1 = pd.DataFrame(df, columns=fval)
#y = df['churn']
x_train_original,x_test_original,y_train_original,y_test_original=train_test_split(df1,y,test_size=0.25)
#clf = svm.SVC(kernel=kern)
clf = GaussianNB()
clf.fit(x_train_original,y_train_original)
predictions=clf.predict(x_test_original)
print("Accuracy =", accuracy_score(y_test_original,predictions))
y_score = clf.predict_proba(x_test_original)[:,1]
precision, recall, _ = precision_recall_curve(y_test_original, y_score)
p1.line(precision, recall, line_width=2,line_alpha=0.6,name ="line2")
average_precision = average_precision_score(y_test_original, predictions)
p1.title.text = "Average Precision Score %f" % average_precision
#print(np.unique(predictions))
tn, fp, fn, tp = confusion_matrix(y_test_original,predictions).ravel()
source.data =dict(fruits=fruits, counts=[tp, fp, tn, fn])
p.title.text = "Model Accuracy %f" % accuracy_score(y_test_original,predictions)
controls = [features]
for control in controls:
control.on_change('value', lambda attr, old, new: update())
sizing_mode = 'fixed' # 'scale_width' also looks nice with this example
inputs = widgetbox(*controls, sizing_mode=sizing_mode)
l = layout([
[desc],
[row(target,stats)],
[inputs,tabs]
],sizing_mode= sizing_mode)
#update() # initial load of the data
curdoc().add_root(l)
curdoc().title = "Churn"