-
Notifications
You must be signed in to change notification settings - Fork 0
/
visuals.py
154 lines (131 loc) · 5.91 KB
/
visuals.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
###########################################
# Suppress matplotlib user warnings
# Necessary for newer version of matplotlib
import warnings
warnings.filterwarnings("ignore", category = UserWarning, module = "matplotlib")
#
# Display inline matplotlib plots with IPython
from IPython import get_ipython
get_ipython().run_line_magic('matplotlib', 'inline')
###########################################
import matplotlib.pyplot as pl
import matplotlib.patches as mpatches
import numpy as np
import pandas as pd
from time import time
from sklearn.metrics import f1_score, accuracy_score
def distribution(data, transformed = False):
"""
Visualization code for displaying skewed distributions of features
"""
# Create figure
fig = pl.figure(figsize = (11,5));
# Skewed feature plotting
for i, feature in enumerate(['capital-gain','capital-loss']):
ax = fig.add_subplot(1, 2, i+1)
ax.hist(data[feature], bins = 25, color = '#00A0A0')
ax.set_title("'%s' Feature Distribution"%(feature), fontsize = 14)
ax.set_xlabel("Value")
ax.set_ylabel("Number of Records")
ax.set_ylim((0, 2000))
ax.set_yticks([0, 500, 1000, 1500, 2000])
ax.set_yticklabels([0, 500, 1000, 1500, ">2000"])
# Plot aesthetics
if transformed:
fig.suptitle("Log-transformed Distributions of Continuous Census Data Features", \
fontsize = 16, y = 1.03)
else:
fig.suptitle("Skewed Distributions of Continuous Census Data Features", \
fontsize = 16, y = 1.03)
fig.tight_layout()
fig.show()
def evaluate(results, accuracy, f1):
"""
Visualization code to display results of various learners.
inputs:
- learners: a list of supervised learners
- stats: a list of dictionaries of the statistic results from 'train_predict()'
- accuracy: The score for the naive predictor
- f1: The score for the naive predictor
"""
# Create figure
fig, ax = pl.subplots(2, 3, figsize = (11,7))
# Constants
bar_width = 0.3
colors = ['#A00000','#00A0A0','#00A000']
#colors = ['#A00000','#00A0A0','#00A000']
# Super loop to plot four panels of data
for k, learner in enumerate(results.keys()):
for j, metric in enumerate(['train_time', 'acc_train', 'f_train', 'pred_time', 'acc_test', 'f_test']):
for i in np.arange(3):
# Creative plot code
ax[j//3, j%3].bar(i+k*bar_width, results[learner][i][metric], width = bar_width, color = colors[k])
ax[j//3, j%3].set_xticks([0.45, 1.45, 2.45])
ax[j//3, j%3].set_xticklabels(["1%", "10%", "100%"])
ax[j//3, j%3].set_xlabel("Training Set Size")
ax[j//3, j%3].set_xlim((-0.1, 3.0))
# Add unique y-labels
ax[0, 0].set_ylabel("Time (in seconds)")
ax[0, 1].set_ylabel("Accuracy Score")
ax[0, 2].set_ylabel("F-score")
ax[1, 0].set_ylabel("Time (in seconds)")
ax[1, 1].set_ylabel("Accuracy Score")
ax[1, 2].set_ylabel("F-score")
# Add titles
ax[0, 0].set_title("Model Training")
ax[0, 1].set_title("Accuracy Score on Training Subset")
ax[0, 2].set_title("F-score on Training Subset")
ax[1, 0].set_title("Model Predicting")
ax[1, 1].set_title("Accuracy Score on Testing Set")
ax[1, 2].set_title("F-score on Testing Set")
# Add horizontal lines for naive predictors
ax[0, 1].axhline(y = accuracy, xmin = -0.1, xmax = 3.0, linewidth = 1, color = 'k', linestyle = 'dashed')
ax[1, 1].axhline(y = accuracy, xmin = -0.1, xmax = 3.0, linewidth = 1, color = 'k', linestyle = 'dashed')
ax[0, 2].axhline(y = f1, xmin = -0.1, xmax = 3.0, linewidth = 1, color = 'k', linestyle = 'dashed')
ax[1, 2].axhline(y = f1, xmin = -0.1, xmax = 3.0, linewidth = 1, color = 'k', linestyle = 'dashed')
# Set y-limits for score panels
ax[0, 1].set_ylim((0, 1))
ax[0, 2].set_ylim((0, 1))
ax[1, 1].set_ylim((0, 1))
ax[1, 2].set_ylim((0, 1))
# # Create patches for the legend
# patches = []
# for i, learner in enumerate(results.keys()):
# patches.append(mpatches.Patch(color = colors[i], label = learner))
# pl.legend(handles = patches, bbox_to_anchor = (0, 3), loc = 'best', borderaxespad = 0., ncol = 3, fontsize = 'x-large')
## pl.legend(handles = patches, bbox_to_anchor = (-.80, 2.53), \
## loc = 'upper center', borderaxespad = 0., ncol = 3, fontsize = 'x-large')
#
# # Aesthetics
# pl.suptitle("Performance Metrics for Three Supervised Learning Models", fontsize = 16, y = 1.10)
# pl.tight_layout()
# pl.show()
patches = []
for i, learner in enumerate(results.keys()):
patches.append(mpatches.Patch(color = colors[i], label = learner))
pl.legend(handles = patches, bbox_to_anchor = (0, 3), \
loc = 'best', borderaxespad = 0., ncol = 3, fontsize = 'x-large')
# Aesthetics
pl.suptitle("Performance Metrics for Three Supervised Learning Models", fontsize = 16, y = 1.10)
#pl.tight_layout()
pl.subplots_adjust(hspace=0.5, wspace=0.4)
pl.show()
def feature_plot(importances, X_train, y_train):
# Display the five most important features
indices = np.argsort(importances)[::-1]
columns = X_train.columns.values[indices[:5]]
values = importances[indices][:5]
# Creat the plot
fig = pl.figure(figsize = (9,5))
pl.title("Normalized Weights for First Five Most Predictive Features", fontsize = 16)
pl.bar(np.arange(5), values, width = 0.6, align="center", color = '#00A000', \
label = "Feature Weight")
pl.bar(np.arange(5) - 0.3, np.cumsum(values), width = 0.2, align = "center", color = '#00A0A0', \
label = "Cumulative Feature Weight")
pl.xticks(np.arange(5), columns)
pl.xlim((-0.5, 4.5))
pl.ylabel("Weight", fontsize = 12)
pl.xlabel("Feature", fontsize = 12)
pl.legend(loc = 'upper center')
pl.tight_layout()
pl.show()