-
Notifications
You must be signed in to change notification settings - Fork 0
/
plot_dist.py
executable file
·375 lines (343 loc) · 14.6 KB
/
plot_dist.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
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
import os
import pandas as pd
import numpy as np
import glob
import read_fy_withcat as rd
import matplotlib.pyplot as plt
import pylab as P
import seaborn as sns
def get_office():
filename = os.getcwd() + '/csv/all_column/sheet-0-all_col.csv'
df = pd.read_csv(filename)
df = df[['Property Name', 'Self-Selected Primary Function']]
df['Property Name'] = df['Property Name'].map(lambda x: x.partition(' ')[0][:8])
df = df[df['Self-Selected Primary Function'] == 'Office']
print len(df)
return set(df['Property Name'].tolist())
def plot_box():
filename = os.getcwd() + '/csv_FY/join/join_2015.csv'
df = pd.read_csv(filename)
df = df[df['eui'] >= 20]
program = ['GP', 'LEED', 'first fuel', 'Shave Energy',
'GSALink Option(26)', 'GSAlink I(55)', 'E4', 'ESPC',
'Energy Star']
length = len(program)
for col in program:
df.boxplot(column='eui', by = [col])
plt.ylim((0, 140))
P.savefig(os.getcwd() + '/plot_FY_annual/box_{0}.png'.format(col),
dpi = 150)
f, axarr = plt.subplots(1, 2 * length, sharey=True, figsize=(20, 10))
fs = 9
for i in range(length):
program_yes = df[df[program[i]] == 1]
t = program_yes['eui'].tolist()
axarr[2 * i].boxplot(np.asarray(t))
axarr[2 * i].set_title((program[i] + '\nY'), fontsize=fs)
program_no = df[df[program[i]] == 0]
t = program_no['eui'].tolist()
axarr[2 * i + 1].boxplot(np.asarray(t))
axarr[2 * i + 1].set_title(('N'), fontsize=fs)
plt.ylim((0, 140))
P.savefig(os.getcwd() + '/plot_FY_annual/box_all.png')
# box_plot by program
def plot_box_pro(theme, ylim, office):
my_dpi = 300
sns.set_style("white")
sns.set_context("paper", font_scale=0.8)
sns.mpl.rc("figure", figsize=(10,5.5))
filename = os.getcwd() + '/csv_FY/join/join_2015.csv'
df = pd.read_csv(filename)
df['GSALink'] = df.apply(lambda row: 1 if row['GSALink Option(26)'] + row['GSAlink I(55)'] > 0 else 0, axis=1)
df.drop(['GSAlink I(55)', 'GSALink Option(26)'], axis=1, inplace=True)
office_set = get_office()
if office:
df = df[df['Building Number'].isin(office_set)]
if theme == 'eui':
df = df[df['eui_elec'] >= 12]
df = df[df['eui_gas'] >= 3]
if theme == 'eui_water':
df = df[df['eui_water'] >= 5]
if theme == 'eui_gas':
df = df[df['eui_gas'] >= 3]
if theme == 'eui_elec':
df = df[df['eui_elec'] >= 12]
# plot only programs
dfs = []
df_temp = df
df_temp = df_temp[df_temp['Total Programs_v2'] > 0]
totalnum = len(set(df_temp['Building Number'].tolist()))
program = ['LEED', 'GP', 'first fuel', 'GSALink', 'E4', 'ESPC',
'Shave Energy', 'Energy Star']
colors = sns.husl_palette(7, l=.5, s=.9) + [(104.0/255,104.0/255,104.0/255)]
color_dict = dict(zip(program, colors))
sizes = []
for col in program:
df_yes = df[df[col] == 1]
df_yes['program'] = col
dfs.append(df_yes)
sizes.append((col, len(df_yes)))
df_all = pd.concat(dfs, ignore_index=True)
df_plot = df_all
size_dict = dict(sizes)
print size_dict
# sort by median
gr = df_plot.groupby('program')
medians = [(name, group[theme].median()) for name, group in gr]
s_medians = sorted(medians, key=lambda x: x[1])
order = [x for (x, _) in s_medians]
order.remove('Energy Star')
order.append('Energy Star')
print theme
print order
ordered_color = [color_dict[x] for x in order]
df_plot = df_all[['program', theme]]
bx = sns.boxplot(x = 'program', y = theme, data = df_plot, fliersize=0, order = order, palette = sns.color_palette(ordered_color))
st = sns.stripplot(x = 'program', y = theme, data = df_plot,
jitter=0.2, edgecolor='gray',
color = 'gray', size=0.3, alpha=0.5, order=order)
xticklabels = ['(n={0})\n{1}+'.format(size_dict[pro], pro) for pro in order]
bx.set(xticklabels=xticklabels)
for tick in bx.xaxis.get_major_ticks():
tick.label.set_fontsize(9)
for tick in bx.yaxis.get_major_ticks():
tick.label.set_fontsize(10)
plt.ylim((0, ylim))
plt.title('Total {0} Buildings'.format(totalnum), fontsize=15)
plt.ylabel(theme.upper(), fontsize=12)
bx.xaxis.set_label_coords(0.5, -0.08)
plt.xlabel('Program', fontsize=12)
plt.ylim((0, ylim))
if office:
P.savefig(os.getcwd() + '/plot_FY_annual/office/box_program_{0}.png'.format(theme), dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
else:
P.savefig(os.getcwd() + '/plot_FY_annual/box_program_{0}.png'.format(theme), dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
plt.close()
def plot_box_vio(theme, ylim, office):
sns.set_style("white")
#sns.set_context("paper", font_scale=3)
sns.set_context("paper", font_scale=0.8)
sns.mpl.rc("figure", figsize=(10,5.5))
colors_2 = sns.husl_palette(7, l=.8, s=.9) + [(192.0/255,192.0/255,192.0/255)]
colors_1 = sns.husl_palette(7, l=.5, s=.9) + [(104.0/255,104.0/255,104.0/255)]
colors = [[x, y] for (x, y) in zip(colors_1, colors_2)]
colors = reduce(lambda x, y: x + y, colors)
office_set = get_office()
filename = os.getcwd() + '/csv_FY/join/join_2015.csv'
df = pd.read_csv(filename)
print ('input length', len(df))
df['GSALink'] = df.apply(lambda row: 1 if row['GSALink Option(26)'] + row['GSAlink I(55)'] > 0 else 0, axis=1)
df.drop(['GSAlink I(55)', 'GSALink Option(26)'], axis=1, inplace=True)
if office:
df = df[df['Building Number'].isin(office_set)]
if theme == 'eui':
df = df[df['eui_elec'] >= 12]
df = df[df['eui_gas'] >= 3]
print ('filter eui', len(df))
'''
p = 0.1
print '\n {0} {1} percentile'.format(theme, p)
print df[theme].quantile(p)
'''
if theme == 'eui_water':
'''
df = df[df['eui_water'] > 0]
p = 0.1
print '\n {0} {1} percentile'.format(theme, p)
df = df[df['eui_water'] > 0]
print df[theme].quantile(p)
'''
df = df[df[theme] >= 5]
print ('filter water', len(df))
if theme == 'eui_gas':
df = df[df[theme] >= 3]
print ('filter gas', len(df))
if theme == 'eui_elec':
df = df[df[theme] >= 12]
print ('filter elec', len(df))
totalnum = len(set(df['Building Number'].tolist()))
print totalnum
program = ['LEED', 'GP', 'first fuel', 'GSALink', 'E4', 'ESPC',
'Shave Energy', 'Energy Star']
ps = [[x + '+', ''] for x in program]
ps = reduce(lambda x, y: x + y, ps)
dfs = []
sizes = []
p_inc = []
for col in program:
df_yes = df[df[col] == 1]
df_yes['program'] = col
df_no = df[df[col] == 0]
df_no['program'] = 'no_' + col
dfs.append(df_yes)
dfs.append(df_no)
sizes.append(len(df_yes))
sizes.append(len(df_no))
percent_inprove = 0
if df_no[theme].median() != 0:
percent_inprove = (df_no[theme].median() - df_yes[theme].median())/df_no[theme].median()
p_inc.append(percent_inprove)
df_all = pd.concat(dfs, ignore_index=True)
df_plot = df_all[['program', theme]]
p_inc = [[str(round(x, 4)*100) + '%', ''] for x in p_inc]
p_inc = reduce(lambda x, y:x + y, p_inc)
yn = ['Yes', 'No'] * len(program)
my_dpi = 300
bx = sns.boxplot(x = 'program', y = theme, data = df_plot, fliersize=0, palette = sns.color_palette(colors))
st = sns.stripplot(x = 'program', y = theme, data = df_plot,
jitter=0.2, edgecolor='gray',
color = 'gray', size=0.3, alpha=0.5)
xticklabels = ['{0}(n={1})\n {2}\n {3}'.format(indi, size, p, p_i) for indi, size, p, p_i in zip(yn, sizes, ps, p_inc)]
bx.set(xticklabels=xticklabels)
for tick in bx.xaxis.get_major_ticks():
tick.label.set_fontsize(7)
for tick in bx.yaxis.get_major_ticks():
tick.label.set_fontsize(10)
plt.title('Total {0} Buildings'.format(totalnum), fontsize=15)
plt.ylabel(theme.upper(), fontsize=12)
bx.xaxis.set_label_coords(0.5, -0.08)
plt.xlabel('Program', fontsize=12)
plt.ylim((0, ylim))
if office:
P.savefig(os.getcwd() + '/plot_FY_annual/office/box_all_{0}.png'.format(theme), dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
else:
P.savefig(os.getcwd() + '/plot_FY_annual/box_all_{0}.png'.format(theme), dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
plt.close()
def plot_elec_eui_ratio():
sns.set_palette(sns.color_palette('Blues', 3))
sns.set_style("white")
sns.set_context("paper", font_scale=1.2)
sns.mpl.rc("figure", figsize=(10,5))
filelist = glob.glob(os.getcwd() + '/csv_FY/agg/*.csv')
dfs = [pd.read_csv(csv) for csv in filelist]
df_all = pd.concat(dfs, ignore_index=True)
df_plot = df_all
df_plot = df_plot[df_plot['eui'] < 10000]
df_plot = df_plot[df_plot['eui'] >= 20]
df_plot['ratio'] = df_plot['eui_elec']/df_plot['eui']
#bx = sns.distplot(df_plot['ratio'], norm_hist=True)
#df_plot.hist(column='ratio')
for p in [0.25, 0.5, 0.75]:
print (p, df_plot['ratio'].quantile(p))
df_plot.boxplot(column='ratio')
plt.show()
plt.close()
# box plot by region, with different global cutoff for elec and gas
def plot_eui_region_filter_elecgas(col, ylim, office):
sns.set_palette(sns.color_palette('Blues', 3))
sns.set_style("white")
sns.set_context("paper", font_scale=0.8)
sns.mpl.rc("figure", figsize=(10,5))
filelist = glob.glob(os.getcwd() + '/csv_FY/agg/*.csv')
dfs = [pd.read_csv(csv) for csv in filelist]
df_all = pd.concat(dfs, ignore_index=True)
df_plot = df_all
indicator = pd.read_csv(os.getcwd() + '/csv_FY/filter_bit/indicator_all.csv')
df_bd = indicator[indicator['good_both'] == 1]
if office:
df_bd = df_bd[df_bd['office'] == 1]
bd_set = set(df_bd['Building Number'].tolist())
df_plot = df_plot[df_plot['Building Number'].isin(bd_set)]
totalnum = len(set(df_plot['Building Number'].tolist()))
st = sns.stripplot(x = 'Region No.', y = col, hue = 'Fiscal Year',
data = df_plot, jitter=0.2, edgecolor='gray',
color = 'gray', size=0.3, alpha=0.5)
bx = sns.boxplot(x = 'Region No.', y = col, hue = 'Fiscal Year',
data = df_plot, fliersize=0)
sizes = df_plot.groupby(['Region No.', 'Fiscal Year']).size()
xticklabels = ['n={0}'.format(size) for group, size in sizes.iteritems()]
xticklabels = ['{0} {1} {2}\nR{3}'.format(xticklabels[i], xticklabels[i + 1], xticklabels[i + 2], i + 1) for i in range(len(sizes)/3)]
bx.set(xticklabels=xticklabels)
plt.legend(loc = 2, bbox_to_anchor=(1, 1))
if 'water' in col:
plt.yticks([10 * x for x in range(4)])
else:
plt.yticks([20 * x for x in range(8)])
for tick in bx.xaxis.get_major_ticks():
tick.label.set_fontsize(6)
for tick in bx.yaxis.get_major_ticks():
tick.label.set_fontsize(10)
plt.ylim((0, ylim))
plt.title('{0} by region and year: total {1} buildings'.format(col, totalnum), fontsize=15)
plt.ylabel(col.upper(), fontsize=12)
my_dpi = 30
if office:
P.savefig(os.getcwd() + '/plot_FY_annual/office/office_{0}_region.png'.format(col), dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
else:
P.savefig(os.getcwd() + '/plot_FY_annual/{0}_region.png'.format(col),
dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
plt.close()
# box plot by region, with different cutoff for each energy type
def plot_eui_region(col, ylim, cut, strict):
sns.set_palette(sns.color_palette('Blues', 3))
sns.set_style("white")
sns.set_context("paper", font_scale=0.7)
sns.mpl.rc("figure", figsize=(10,5))
filelist = glob.glob(os.getcwd() + '/csv_FY/agg/*.csv')
dfs = [pd.read_csv(csv) for csv in filelist]
df_all = pd.concat(dfs, ignore_index=True)
df_plot = df_all
df_plot = df_plot[df_plot['eui'] < 10000]
if strict:
df_plot = df_plot[df_plot[col] > cut]
else:
df_plot = df_plot[df_plot[col] >= cut]
totalnum = len(set(df_plot['Building Number'].tolist()))
st = sns.stripplot(x = 'Region No.', y = col, hue = 'Fiscal Year',
data = df_plot, jitter=0.2, edgecolor='gray',
color = 'gray', size=0.3, alpha=0.5)
bx = sns.boxplot(x = 'Region No.', y = col, hue = 'Fiscal Year',
data = df_plot, fliersize=0)
sizes = df_plot.groupby(['Region No.', 'Fiscal Year']).size()
#xticklabels = ['{0}\nn={1}'.format(group, size) for group, size in sizes.iteritems()]
xticklabels = ['n={0}'.format(size) for group, size in sizes.iteritems()]
xticklabels = ['{0} {1} {2}\nR{3}'.format(xticklabels[i], xticklabels[i + 1], xticklabels[i + 2], i + 1) for i in range(len(sizes)/3)]
bx.set(xticklabels=xticklabels)
plt.legend(loc = 2, bbox_to_anchor=(1, 1))
if 'water' in col:
plt.yticks([10 * x for x in range(4)])
else:
plt.yticks([20 * x for x in range(8)])
plt.ylim((0, ylim))
plt.title('{0} by region and year: total {1} buildings'.format(col, totalnum))
my_dpi = 300
P.savefig(os.getcwd() + '/plot_FY_annual/{0}_region.png'.format(col),
dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
plt.close()
'''
g = sns.FacetGrid(df_plot, col='Region No.', size=4, aspect=0.4)
g.map(sns.boxplot, 'Region No.', 'eui', 'Fiscal Year')
g.map(sns.stripplot, 'Region No.', 'eui', 'Fiscal Year')
plt.ylim((0, 140))
plt.show()
P.savefig(os.getcwd() + '/plot_FY_annual/eui_region_sub.png',
dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
plt.close()
sns.violinplot(x = 'Region No.', y = 'eui', hue = 'Fiscal Year',
data = df_plot)
plt.ylim((0, 140))
my_dpi = 300
P.savefig(os.getcwd() + '/plot_FY_annual/eui_region_vio.png',
dpi = my_dpi, figsize = (2000/my_dpi, 500/my_dpi))
plt.close()
'''
def region_boxplot():
themes = ['eui', 'eui_elec', 'eui_gas', 'eui_water']
ylims = [140, 120, 120, 30]
for theme, ylim in zip(themes, ylims):
plot_eui_region_filter_elecgas(theme, ylim, True)
plot_eui_region_filter_elecgas(theme, ylim, False)
def main():
#plot_box()
themes = ['eui', 'eui_elec', 'eui_gas', 'eui_water']
ylims = [140, 100, 100, 30]
for theme, ylim in zip(themes, ylims):
'''
plot_box_vio(theme, ylim, False)
plot_box_vio(theme, ylim, True)
'''
plot_box_pro(theme, ylim, False)
plot_box_pro(theme, ylim, True)
#region_boxplot()
#plot_elec_eui_ratio()
main()