-
Notifications
You must be signed in to change notification settings - Fork 1
/
dataset_analyse_nberbaci.py
392 lines (312 loc) · 15.6 KB
/
dataset_analyse_nberbaci.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
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
"""
Analyse Tables, Plots and Construct Meta Data for NBERBACI Data
"""
from __future__ import division
import os
import gc
import glob
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
#-Years-#
Y6200 = False
Y7400 = True
Y8400 = True
#---------#
#-Control-#
#---------#
DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES = False
DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES = False
DATASET_SIMPLESTATS_TABLE = True
DATASET_PERCENTWORLDTRADE_PLOTS = False
#-Helper Functions-#
def split_filenames(fl):
dataset, data_type, classification, years, harmonised = fl.split("-")
classification, product_level = classification[:-2], classification[-1:]
return dataset, data_type, classification, product_level
#----------#
#-DATASETS-#
#----------#
#--------------#
#-1962 to 2012-#
#--------------#
if Y6200:
from dataset_info import RESULTS_DIR, TARGET_DATASET_DIR
SOURCE_DIR = TARGET_DATASET_DIR["nberbaci96"]
STORES = glob.glob(SOURCE_DIR + "*.h5")
RESULTS_DIR = RESULTS_DIR["nberbaci96"]
## ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
## ---> Product Composition Tables <--- ##
## ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
if DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES:
print "Running DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES ..."
DIR = RESULTS_DIR + "intertemporal-productcodes/"
for store in STORES:
print "Computing Composition Tables for: %s" % store
dataset, data_type, classification, product_level = split_filenames(store.split("/")[-1])
store = pd.HDFStore(store)
for dataset in store.keys():
print "Computing table for dataset: %s ..." % dataset
dataset = dataset.strip("/")
intertemp_product = store[dataset].groupby(["year", "sitc%s"%product_level]).sum().unstack("year")
intertemp_product.columns = intertemp_product.columns.droplevel()
intertemp_product.to_excel(DIR + "intertemporal_product_%s_%sl%s_%s.xlsx"%(data_type, classification, product_level, dataset))
#-Memory Release-#
del intertemp_product
gc.collect()
store.close()
## ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
## ---> Country Composition Tables <--- ##
## ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
if DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES:
print "Running DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES ..."
DIR = RESULTS_DIR + "intertemporal-countrycodes/"
for store in STORES:
print "Computing Composition Tables for: %s" % store
dataset, data_type, classification, product_level = split_filenames(store.split("/")[-1])
store = pd.HDFStore(store)
for dataset in store.keys():
print "Computing table for dataset: %s ..." % dataset
dataset = dataset.strip("/")
if data_type == "export":
intertemp_country = store[dataset].groupby(["year", "eiso3c"]).sum().unstack("year")
if data_type == "import":
intertemp_country = store[dataset].groupby(["year", "iiso3c"]).sum().unstack("year")
else:
continue
intertemp_country.columns = intertemp_country.columns.droplevel()
intertemp_country.to_excel(DIR + "intertemporal_country_%s_%sl%s_%s.xlsx"%(data_type, classification, product_level, dataset))
#-Memory Release-#
del intertemp_country
gc.collect()
store.close()
## ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
## ----> SIMPLE STATS TABLES <---- ##
## ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~ ##
if DATASET_SIMPLESTATS_TABLE:
from pyeconlab.trade.util import describe
print "Running DATASET_SIMPLESTATS_TABLE: ..."
DIR = RESULTS_DIR + "tables/"
for dataset_file in STORES:
print "Running STATS on File %s" % dataset_file
store = pd.HDFStore(dataset_file)
for dataset in sorted(store.keys()):
dataset = dataset.strip("/") #Remove Directory Structure
print "Computing SIMPLE STATS for dataset: %s" % dataset
data = pd.read_hdf(dataset_file, key=dataset)
productcode = "".join(dataset_file.split("/")[-1].split("-")[2].split("r2l"))
dataset_table = describe(data, table_name=dataset, productcode=productcode)
#-Memory Reduction-#
del data
gc.collect()
if dataset == "A":
table = dataset_table
else:
table = table.merge(dataset_table, left_index=True, right_index=True)
store.close()
#-Excel Table-#
fl = dataset_file.split("/")[-1].split(".")[0] + "_stats" + ".xlsx"
table.to_excel(DIR + fl)
#-Latex Snippet-#
fl = dataset_file.split("/")[-1].split(".")[0] + "_stats" + ".tex"
with open(DIR + fl, "w") as latex_file:
latex_file.write(table.to_latex())
#-!!-Note: These are not truely valid comparisons as there are ~40 countries droppped from CEPII BACI. -!!-#
#-!!-But Surprising the values drop to ~90% of values in original dataset-!!-#
if DATASET_PERCENTWORLDTRADE_PLOTS:
print "DATASET_PERCENTWORLDTRADE_PLOTS ... "
DIR = RESULTS_DIR + "plots/percent_world_values/"
def join_values(row):
""" Join Rows and Average if both values are not np.nan """
if np.isnan(row["NBER"]) and np.isnan(row["BACI"]):
return np.nan
elif np.isnan(row["NBER"]):
return row["BACI"]
elif np.isnan(row["BACI"]):
return row["NBER"]
else:
return (row["NBER"] + row["BACI"]) / 2
#-World Values-#
fl = "./output/dataset/baci96/raw_baci_world_yearly-1998to2012.h5"
baci_world_values = pd.read_hdf(fl, key="World")["value"]
baci_world_values.name = "BACI"
fl = "./output/dataset/nber/raw_nber_world_yearly-1962to2000.h5"
nber_world_values = pd.read_hdf(fl, key="World")["value"]
nber_world_values.name = "NBER"
world_values = pd.DataFrame([baci_world_values, nber_world_values]).T
world_values["value"] = world_values.apply(lambda row: join_values(row), axis=1) #-Average Overlap Years-#
world_values = world_values["value"]
for dataset_file in STORES:
print "Producing GRAPH on File %s" % dataset_file
store = pd.HDFStore(dataset_file)
datasets = store.keys()
for dataset in sorted(datasets):
print "Computing GRAPH for dataset: %s" % dataset
data = pd.read_hdf(dataset_file, key=dataset)
yearly_values = data.groupby(["year"]).sum()["value"]
percent_values = yearly_values.div(world_values)*100
fig = percent_values.plot(title="Dataset: %s (%s)"%(dataset, dataset_file))
plt.savefig(DIR + "%s_%s_percent_wld.pdf"%(dataset, dataset_file.split('/')[-1].split('.')[0]))
plt.close()
#-Memory Release-#
del data
gc.collect()
store.close()
#--------------#
#-1974 to 2012-#
#--------------#
if Y7400:
LOCAL_DIR = "Y7400/"
from dataset_info import RESULTS_DIR, TARGET_DATASET_DIR
SOURCE_DIR = TARGET_DATASET_DIR["nberbaci96"]
STORES = glob.glob(SOURCE_DIR + LOCAL_DIR + "*.h5")
RESULTS_DIR = RESULTS_DIR["nberbaci96"]
## ---> Product Composition Tables <--- ##
if DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES:
print "Running DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES ..."
DIR = RESULTS_DIR + "intertemporal-productcodes/" + LOCAL_DIR
for store in STORES:
print "Computing Composition Tables for: %s" % store
dataset, data_type, classification, product_level = split_filenames(store.split("/")[-1])
store = pd.HDFStore(store)
for dataset in store.keys():
print "Computing table for dataset: %s ..." % dataset
dataset = dataset.strip("/")
intertemp_product = store[dataset].groupby(["year", "sitc%s"%product_level]).sum().unstack("year")
intertemp_product.columns = intertemp_product.columns.droplevel()
intertemp_product.to_excel(DIR + "intertemporal_product_%s_%sl%s_%s.xlsx"%(data_type, classification, product_level, dataset))
#-Memory Release-#
del intertemp_product
gc.collect()
store.close()
## ---> Country Composition Tables <--- ##
if DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES:
print "Running DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES ..."
DIR = RESULTS_DIR + "intertemporal-countrycodes/" + LOCAL_DIR
for store in STORES:
print "Computing Composition Tables for: %s" % store
dataset, data_type, classification, product_level = split_filenames(store.split("/")[-1])
store = pd.HDFStore(store)
for dataset in store.keys():
print "Computing table for dataset: %s ..." % dataset
dataset = dataset.strip("/")
if data_type == "export":
intertemp_country = store[dataset].groupby(["year", "eiso3c"]).sum().unstack("year")
if data_type == "import":
intertemp_country = store[dataset].groupby(["year", "iiso3c"]).sum().unstack("year")
else:
continue
intertemp_country.columns = intertemp_country.columns.droplevel()
intertemp_country.to_excel(DIR + "intertemporal_country_%s_%sl%s_%s.xlsx"%(data_type, classification, product_level, dataset))
#-Memory Release-#
del intertemp_country
gc.collect()
store.close()
## ----> SIMPLE STATS TABLES <---- ##
if DATASET_SIMPLESTATS_TABLE:
from pyeconlab.trade.util import describe
print "Running DATASET_SIMPLESTATS_TABLE: ..."
DIR = RESULTS_DIR + "tables/" + LOCAL_DIR
for dataset_file in STORES:
print "Running STATS on File %s" % dataset_file
store = pd.HDFStore(dataset_file)
for dataset in sorted(store.keys()):
dataset = dataset.strip("/") #Remove Directory Structure
print "Computing SIMPLE STATS for dataset: %s" % dataset
data = pd.read_hdf(dataset_file, key=dataset)
productcode = "".join(dataset_file.split("/")[-1].split("-")[2].split("r2l"))
dataset_table = describe(data, table_name=dataset, productcode=productcode)
#-Memory Reduction-#
del data
gc.collect()
if dataset == "A":
table = dataset_table
else:
table = table.merge(dataset_table, left_index=True, right_index=True)
store.close()
#-Excel Table-#
fl = dataset_file.split("/")[-1].split(".")[0] + "_stats" + ".xlsx"
table.to_excel(DIR + fl)
#-Latex Snippet-#
fl = dataset_file.split("/")[-1].split(".")[0] + "_stats" + ".tex"
with open(DIR + fl, "w") as latex_file:
latex_file.write(table.to_latex())
#--------------#
#-1984 to 2012-#
#--------------#
if Y8400:
LOCAL_DIR = "Y8400/"
from dataset_info import RESULTS_DIR, TARGET_DATASET_DIR
SOURCE_DIR = TARGET_DATASET_DIR["nberbaci96"]
STORES = glob.glob(SOURCE_DIR + LOCAL_DIR + "*.h5")
RESULTS_DIR = RESULTS_DIR["nberbaci96"]
## ---> Product Composition Tables <--- ##
if DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES:
print "Running DATASET_PRODUCTCODE_INTERTEMPORAL_TABLES ..."
DIR = RESULTS_DIR + "intertemporal-productcodes/" + LOCAL_DIR
for store in STORES:
print "Computing Composition Tables for: %s" % store
dataset, data_type, classification, product_level = split_filenames(store.split("/")[-1])
store = pd.HDFStore(store)
for dataset in store.keys():
print "Computing table for dataset: %s ..." % dataset
dataset = dataset.strip("/")
intertemp_product = store[dataset].groupby(["year", "sitc%s"%product_level]).sum().unstack("year")
intertemp_product.columns = intertemp_product.columns.droplevel()
intertemp_product.to_excel(DIR + "intertemporal_product_%s_%sl%s_%s.xlsx"%(data_type, classification, product_level, dataset))
#-Memory Release-#
del intertemp_product
gc.collect()
store.close()
## ---> Country Composition Tables <--- ##
if DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES:
print "Running DATASET_COUNTRYCODE_INTERTEMPORAL_TABLES ..."
DIR = RESULTS_DIR + "intertemporal-countrycodes/" + LOCAL_DIR
for store in STORES:
print "Computing Composition Tables for: %s" % store
dataset, data_type, classification, product_level = split_filenames(store.split("/")[-1])
store = pd.HDFStore(store)
for dataset in store.keys():
print "Computing table for dataset: %s ..." % dataset
dataset = dataset.strip("/")
if data_type == "export":
intertemp_country = store[dataset].groupby(["year", "eiso3c"]).sum().unstack("year")
if data_type == "import":
intertemp_country = store[dataset].groupby(["year", "iiso3c"]).sum().unstack("year")
else:
continue
intertemp_country.columns = intertemp_country.columns.droplevel()
intertemp_country.to_excel(DIR + "intertemporal_country_%s_%s_%s.xlsx"%(data_type, classification, dataset))
#-Memory Release-#
del intertemp_country
gc.collect()
store.close()
## ----> SIMPLE STATS TABLES <---- ##
if DATASET_SIMPLESTATS_TABLE:
from pyeconlab.trade.util import describe
print "Running DATASET_SIMPLESTATS_TABLE: ..."
DIR = RESULTS_DIR + "tables/" + LOCAL_DIR
for dataset_file in STORES:
print "Running STATS on File %s" % dataset_file
store = pd.HDFStore(dataset_file)
for dataset in sorted(store.keys()):
dataset = dataset.strip("/") #Remove Directory Structure
print "Computing SIMPLE STATS for dataset: %s" % dataset
data = pd.read_hdf(dataset_file, key=dataset)
productcode = "".join(dataset_file.split("/")[-1].split("-")[2].split("r2l"))
dataset_table = describe(data, table_name=dataset, productcode=productcode)
#-Memory Reduction-#
del data
gc.collect()
if dataset == "A":
table = dataset_table
else:
table = table.merge(dataset_table, left_index=True, right_index=True)
store.close()
#-Excel Table-#
fl = dataset_file.split("/")[-1].split(".")[0] + "_stats" + ".xlsx"
table.to_excel(DIR + fl)
#-Latex Snippet-#
fl = dataset_file.split("/")[-1].split(".")[0] + "_stats" + ".tex"
with open(DIR + fl, "w") as latex_file:
latex_file.write(table.to_latex())