-
Notifications
You must be signed in to change notification settings - Fork 0
/
util.py
307 lines (245 loc) · 10.8 KB
/
util.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
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
from sklearn.metrics import confusion_matrix
from sklearn.metrics import classification_report
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import StandardScaler
from sklearn.preprocessing import LabelEncoder
import seaborn as sns
_categories=['blues', 'classical', 'country', 'disco', 'hiphop', 'jazz', 'metal', 'pop', 'reggae', 'rock']
encoder = LabelEncoder()
def load_preprocess_xy(file_path, split_percentage, scale_x, encode_y, dummify_y):
dataset = pd.read_csv(file_path)
X = dataset.iloc[:, 1:59].values
y = dataset.iloc[:, 59].values
if encode_y:
y = encoder.fit_transform(y)
if scale_x:
sc_X = StandardScaler()
X = sc_X.fit_transform(X) #TODO should we scale test and train separately? Yes, but wont have much difference?
if dummify_y:
y = pd.get_dummies(y).values
if split_percentage > 0:
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size = split_percentage, random_state = 0)
return X_train, X_test, y_train, y_test
return X, y
def get_accuracy(cm):
sum = 0
for i in range(cm.shape[0]):
sum = sum + cm[i][i]
return 100*(sum/np.sum(cm))
def print_cm_cd(y_test, y_pred):
cm = confusion_matrix(y_test, y_pred)
#print("Accuracy: ", get_accuracy(cm))
make_confusion_matrix(cm, figsize=(10, 6.5), categories=_categories, title="Confusion Matrix")
if y_test.dtype == 'int32' or y_test.dtype == 'int64':
_classification_report = classification_report(encoder.inverse_transform(y_test), encoder.inverse_transform(y_pred), labels=_categories)
else:
_classification_report = classification_report(y_test, y_pred, labels=_categories)
# print(_classification_report)
_classification_report = "\n".join(list(_classification_report.split("\n")[i] for i in [0,1,2,3,4,5,6,7,8,9,10,11,12,15]))
# print(_classification_report)
# _classification_report = "\n".join(list(_classification_report.split("\n")[i] for i in [0,1,2,3,4,5,6,7,8,9,10,11,12,15])).replace("weighted avg", " avg / total")
plot_classification_report(_classification_report)
def fit_predict_print(fit_predict_function, X_train, y_train, X_test, y_test):
y_pred = fit_predict_function(X_train, y_train, X_test)
if y_pred.dtype != y_test.dtype:
y_pred = np.argmax(y_pred,axis=1)
y_test = np.argmax(y_test,axis=1)
print_cm_cd(y_test, y_pred)
def fit_predict_print_unsupervised(fit_predict_function, X_train, X_test, y_test):
y_pred = fit_predict_function(X_train, X_test)
if y_test is not None:
print_cm_cd(y_test, y_pred)
def search_fit_predict_print(fit_predict_function, X_train, y_train, X_test, y_test):
ensemble, y_pred = fit_predict_function(X_train, y_train, X_test)
cm = confusion_matrix(y_test, y_pred)
print_cm_cd(y_test, y_pred)
# Ref:
# https://github.com/DTrimarchi10/confusion_matrix
# https://medium.com/@dtuk81/confusion-matrix-visualization-fc31e3f30fea
def make_confusion_matrix(cf,
group_names=None,
categories='auto',
count=True,
percent=True,
cbar=True,
xyticks=True,
xyplotlabels=True,
sum_stats=True,
figsize=None,
cmap='Blues',
title=None):
'''
This function will make a pretty plot of an sklearn Confusion Matrix cm using a Seaborn heatmap visualization.
Arguments
---------
cf: confusion matrix to be passed in
group_names: List of strings that represent the labels row by row to be shown in each square.
categories: List of strings containing the categories to be displayed on the x,y axis. Default is 'auto'
count: If True, show the raw number in the confusion matrix. Default is True.
normalize: If True, show the proportions for each category. Default is True.
cbar: If True, show the color bar. The cbar values are based off the values in the confusion matrix.
Default is True.
xyticks: If True, show x and y ticks. Default is True.
xyplotlabels: If True, show 'True Label' and 'Predicted Label' on the figure. Default is True.
sum_stats: If True, display summary statistics below the figure. Default is True.
figsize: Tuple representing the figure size. Default will be the matplotlib rcParams value.
cmap: Colormap of the values displayed from matplotlib.pyplot.cm. Default is 'Blues'
See http://matplotlib.org/examples/color/colormaps_reference.html
title: Title for the heatmap. Default is None.
'''
# CODE TO GENERATE TEXT INSIDE EACH SQUARE
blanks = ['' for i in range(cf.size)]
if group_names and len(group_names)==cf.size:
group_labels = ["{}\n".format(value) for value in group_names]
else:
group_labels = blanks
if count:
group_counts = ["{0:0.0f}\n".format(value) for value in cf.flatten()]
else:
group_counts = blanks
if percent:
group_percentages = ["{0:.2%}".format(value) for value in cf.flatten()/np.sum(cf)]
else:
group_percentages = blanks
box_labels = [f"{v1}{v2}{v3}".strip() for v1, v2, v3 in zip(group_labels,group_counts,group_percentages)]
box_labels = np.asarray(box_labels).reshape(cf.shape[0],cf.shape[1])
# CODE TO GENERATE SUMMARY STATISTICS & TEXT FOR SUMMARY STATS
if sum_stats:
#Accuracy is sum of diagonal divided by total observations
accuracy = np.trace(cf) / float(np.sum(cf))
#if it is a binary confusion matrix, show some more stats
if len(cf)==2:
#Metrics for Binary Confusion Matrices
precision = cf[1,1] / sum(cf[:,1])
recall = cf[1,1] / sum(cf[1,:])
f1_score = 2*precision*recall / (precision + recall)
stats_text = "\n\nAccuracy={:0.3f}\nPrecision={:0.3f}\nRecall={:0.3f}\nF1 Score={:0.3f}".format(
accuracy,precision,recall,f1_score)
else:
stats_text = "\n\nAccuracy={:0.3f}".format(accuracy)
else:
stats_text = ""
# SET FIGURE PARAMETERS ACCORDING TO OTHER ARGUMENTS
if figsize==None:
#Get default figure size if not set
figsize = plt.rcParams.get('figure.figsize')
if xyticks==False:
#Do not show categories if xyticks is False
categories=False
# MAKE THE HEATMAP VISUALIZATION
plt.figure(figsize=figsize)
sns.heatmap(cf,annot=box_labels,fmt="",cmap=cmap,cbar=cbar,xticklabels=categories,yticklabels=categories)
if xyplotlabels:
plt.ylabel('True label')
plt.xlabel('Predicted label' + stats_text)
else:
plt.xlabel(stats_text)
if title:
plt.title(title)
plt.show()
# Classification report visualization source: https://stackoverflow.com/a/34304414
def show_values(pc, fmt="%.2f", **kw):
'''
Heatmap with text in each cell with matplotlib's pyplot
Source: https://stackoverflow.com/a/25074150/395857
By HYRY
'''
pc.update_scalarmappable()
ax = pc.axes
#ax = pc.axes# FOR LATEST MATPLOTLIB
#Use zip BELOW IN PYTHON 3
for p, color, value in zip(pc.get_paths(), pc.get_facecolors(), pc.get_array()):
x, y = p.vertices[:-2, :].mean(0)
if np.all(color[:3] > 0.5):
color = (0.0, 0.0, 0.0)
else:
color = (1.0, 1.0, 1.0)
ax.text(x, y, fmt % value, ha="center", va="center", color=color, **kw)
def cm2inch(*tupl):
'''
Specify figure size in centimeter in matplotlib
Source: https://stackoverflow.com/a/22787457/395857
By gns-ank
'''
inch = 2.54
if type(tupl[0]) == tuple:
return tuple(i/inch for i in tupl[0])
else:
return tuple(i/inch for i in tupl)
def heatmap(AUC, title, xlabel, ylabel, xticklabels, yticklabels, figure_width=40, figure_height=20, correct_orientation=False, cmap='RdBu'):
'''
Inspired by:
- https://stackoverflow.com/a/16124677/395857
- https://stackoverflow.com/a/25074150/395857
'''
# Plot it out
fig, ax = plt.subplots()
#c = ax.pcolor(AUC, edgecolors='k', linestyle= 'dashed', linewidths=0.2, cmap='RdBu', vmin=0.0, vmax=1.0)
c = ax.pcolor(AUC, edgecolors='k', linestyle= 'dashed', linewidths=0.2, cmap=cmap)
# put the major ticks at the middle of each cell
ax.set_yticks(np.arange(AUC.shape[0]) + 0.5, minor=False)
ax.set_xticks(np.arange(AUC.shape[1]) + 0.5, minor=False)
# set tick labels
#ax.set_xticklabels(np.arange(1,AUC.shape[1]+1), minor=False)
ax.set_xticklabels(xticklabels, minor=False)
ax.set_yticklabels(yticklabels, minor=False)
# set title and x/y labels
plt.title(title)
plt.xlabel(xlabel)
plt.ylabel(ylabel)
# Remove last blank column
plt.xlim( (0, AUC.shape[1]) )
# Turn off all the ticks
ax = plt.gca()
for t in ax.xaxis.get_major_ticks():
t.tick1On = False
t.tick2On = False
for t in ax.yaxis.get_major_ticks():
t.tick1On = False
t.tick2On = False
# Add color bar
plt.colorbar(c)
# Add text in each cell
show_values(c)
# Proper orientation (origin at the top left instead of bottom left)
if correct_orientation:
ax.invert_yaxis()
ax.xaxis.tick_top()
# resize
fig = plt.gcf()
#fig.set_size_inches(cm2inch(40, 20))
#fig.set_size_inches(cm2inch(40*4, 20*4))
fig.set_size_inches(cm2inch(figure_width, figure_height))
plt.show()
def plot_classification_report(classification_report, title='Classification report ', cmap='RdBu'):
'''
Plot scikit-learn classification report.
Extension based on https://stackoverflow.com/a/31689645/395857
'''
lines = classification_report.split('\n')
classes = []
plotMat = []
support = []
class_names = []
for line in lines[2 : (len(lines) - 2)]:
t = line.strip().split()
if len(t) < 2: continue
classes.append(t[0])
v = [float(x) for x in t[1: len(t) - 1]]
support.append(int(t[-1]))
class_names.append(t[0])
# print(v)
plotMat.append(v)
# print('plotMat: {0}'.format(plotMat))
# print('support: {0}'.format(support))
xlabel = 'Metrics'
ylabel = 'Classes'
xticklabels = ['Precision', 'Recall', 'F1-score']
yticklabels = ['{0} ({1})'.format(class_names[idx], sup) for idx, sup in enumerate(support)]
figure_width = 25
figure_height = len(class_names) + 7
correct_orientation = False
heatmap(np.array(plotMat), title, xlabel, ylabel, xticklabels, yticklabels, figure_width, figure_height, correct_orientation, cmap=cmap)