def main(file_path, year, output_path, prev_path, prev5_path):
start = time.time()
step = 0
geo_depths = [2, 4, 6, 7, 8] # state, meso, micro, planning region, munic
d = pd.HDFStore(os.path.abspath(os.path.join(output_path,'rais.h5')))
step+=1; print; print '''STEP {0}: \nImport file to pandas dataframe'''.format(step)
rais_df = to_df(file_path, False, calc_d_id=True)
step+=1; print; print '''STEP {0}: \nAggregate with Demographics'''.format(step)
tables = aggregate_demographics(rais_df, geo_depths)
for table_name, table_data in tables.items():
table_data = add_column_length(table_name, table_data)
# print table_data.head()
if prev_path:
step+=1; print; print '''STEP {0}: \nCalculate 1 year growth'''.format(step)
for t_name, t in tables.items():
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name, calc_d_id=True)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] + list(t_prev.index.names)[:-1])
tables[t_name] = calc_growth(t, t_prev)
print tables[t_name].head()
# sys.exit()
if prev5_path:
step+=1; print; print '''STEP {0}: \nCalculate 5 year growth'''.format(step)
prev_file = os.path.join(prev5_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name, calc_d_id=True)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] + list(t_prev.index.names)[:-1])
# t_prev = to_df(prev_file, t_name)
tables[t_name] = calc_growth(tables[t_name], t_prev, 5)
print; print '''FINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
if not os.path.exists(output_path):
os.makedirs(output_path)
new_file_path = os.path.abspath(os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True, float_format="%.2f")
print("--- %s minutes ---" % str((time.time() - start)/60))
def main(cur_path, year, output_path, prev_path, prev5_path, demographic_mode):
start = time.time()
step = 0
tables_reg = ["yb", "yi", "yo", "ybi", "ybo", "yio", "ybio"]
if demographic_mode:
tables_reg = ["ybd", "yid", "yod", "ybid", "ybod" ]
for t_name in tables_reg:
cur_file = os.path.join(cur_path, "{0}.tsv.bz2".format(t_name))
print cur_file
t = to_df(cur_file, t_name, calc_d_id=demographic_mode)
step+=1; print; print '''STEP {0}: \nCalculate 1 year growth'''.format(step)
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name, calc_d_id=demographic_mode)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] + list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev)
print t.head()
if prev5_path:
step+=1; print; print '''STEP {0}: \nCalculate 5 year growth'''.format(step)
prev_file = os.path.join(prev5_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name, calc_d_id=demographic_mode)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] + list(t_prev.index.names)[:-1])
print t_prev.head()
t = calc_growth(t, t_prev, 5)
print t.head()
if not os.path.exists(output_path):
os.makedirs(output_path)
print "Saving!"
new_file_path = os.path.abspath(os.path.join(output_path, "{0}_with_growth.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True, float_format="%.2f")
print("--- %s minutes ---" % str((time.time() - start)/60))
def calc_growth(year, current_year_file_path, prev_year_file_path, prev5_year_file_path):
tbl_name = extract_tbl_name(current_year_file_path)
current_year_tbl = to_df(current_year_file_path, tbl_name)
for prev_path, years_ago in [(prev_year_file_path, 1), (prev5_year_file_path, 5)]:
if not prev_path: continue
prev_year_tbl = to_df(prev_path, tbl_name)
prev_year_tbl = prev_year_tbl.reset_index(level="year")
prev_year_tbl["year"] = int(year)
prev_year_tbl = prev_year_tbl.set_index("year", append=True)
prev_year_tbl = prev_year_tbl.reorder_levels(["year"] + list(prev_year_tbl.index.names)[:-1])
current_year_tbl = do_growth(current_year_tbl, prev_year_tbl, years_ago)
return (tbl_name, current_year_tbl)
def main(file_path, year, output_path, prev_path, prev5_path):
print "\nHEDU YEAR: {0}\n".format(year)
pre_check()
output_path = os.path.join(output_path, str(year))
if not os.path.exists(output_path):
os.makedirs(output_path)
hdf_store = pd.HDFStore(os.path.abspath(os.path.join(output_path, 'hedu_data.h5')))
print '''\nImport file to pandas dataframe'''
if "hedu_df" in hdf_store:
hedu_df = hdf_store['hedu_df']
else:
hedu_df = to_df(file_path, year)
try:
hdf_store['hedu_df'] = hedu_df
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
hdf_store.close()
os.remove(os.path.join(output_path, 'hedu_data.h5'))
tables_list = ["yb", "yu", "yc", "ybc", "ybu", "yuc", "ybuc"]
index_lookup = {"y": "year", "b": "bra_id", "c": "course_hedu_id", "u": "university_id"}
for table_name in tables_list:
indexes = [index_lookup[l] for l in table_name]
print '''\nAggregating {0}'''.format(table_name)
aggregated_df = aggregate(indexes, hedu_df)
print '''Adding length column to {0}'''.format(table_name)
aggregated_df = add_column_length(table_name, aggregated_df)
print '''Renaming {0} columns'''.format(table_name)
aggregated_df.rename(columns={"student_id": "students"}, inplace=True)
if 'u' not in table_name:
aggregated_df.rename(columns={"university_id": "num_universities"}, inplace=True)
if prev_path:
print '''\nCalculating {0} 1 year growth'''.format(table_name)
previous_df = open_prev_df(prev_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df, ['enrolled', 'graduates'])
if prev5_path:
print '''\nCalculating {0} 5 year growth'''.format(table_name)
previous_df = open_prev_df(prev5_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df, ['enrolled', 'graduates'], 5)
if table_name == "ybuc":
print '''Calculating RCAs'''
ybc = calc_rca(aggregated_df, year)
new_file_path = os.path.abspath(os.path.join(output_path, "ybc_rca.tsv.bz2"))
ybc.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
file_name = table_name + ".tsv.bz2"
print '''Save {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(os.path.join(output_path, file_name))
aggregated_df.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
def open_prev_df(prev_path, table_name, year, indexes):
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(table_name))
previous_df = to_df(prev_file, year, indexes)
previous_df = previous_df.reset_index(level="year")
previous_df["year"] = int(year)
previous_df = previous_df.set_index("year", append=True)
previous_df = previous_df.reorder_levels(["year"] + list(previous_df.index.names)[:-1])
return previous_df
def open_prev_df(prev_path, table_name, year, indexes):
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(table_name))
previous_df = to_df(prev_file, year, indexes)
previous_df = previous_df.reset_index(level="year")
previous_df["year"] = int(year)
previous_df = previous_df.set_index("year", append=True)
previous_df = previous_df.reorder_levels(
["year"] + list(previous_df.index.names)[:-1])
return previous_df
def main(file_path, table):
# This should create the folder if it's not there yet
if not os.path.exists(file_path): os.makedirs(file_path)
# Reading the csv, getting a dataframe from pd.read_csv
data_frame = to_df(sys.argv[1])
connection = MySQLdb.connect(host=os.environ["DB_HOST"], user=os.environ["DB_USER"], passwd=os.environ["DB_PW"], db=os.environ["DB_NAME"])
data_frame.to_sql(table, connection, flavor='mysql', if_exists='replace', index=False, chunksize=650000)
def main(file_path, year, output_path):
pre_check()
output_path = os.path.join(output_path, str(year))
if not os.path.exists(output_path): os.makedirs(output_path)
print "Output Path=", output_path
# d = pd.HDFStore(os.path.abspath(os.path.join(output_path,'sc_data.h5')))
print; print '''STEP 1: \nImport file to pandas dataframe'''
hdf_filepath = output_path + "/store_df.h5"
print "LOOKING for HDF file at location ", hdf_filepath
if os.path.exists(hdf_filepath):
print "READING HDF"
df = pd.read_hdf(hdf_filepath, 'table')
else:
print "No HDF file. Need to create DF"
df = to_df(file_path, False)
print "SAVING HDF to", hdf_filepath
df.to_hdf(hdf_filepath, 'table')
print; print "Step 2: aggregate"
from _aggregate import agg_rules
pk_lookup = {"y": "year", "d": "d_id", "b": "bra_id", "c": "course_sc_id", "s": "school_id"}
tables_list = ["yb", "ybd", "yd", "ybs", "yc", "ybc", "ybcd"]
for table_name in tables_list:
pk = [pk_lookup[l] for l in table_name]
print "working on", table_name
dems = ['gender', 'color', 'loc', 'school_type'] if "d" in table_name else ['']
for dem in dems:
print '''\nSTEP 2: Aggregate {0}'''.format(dem)
tbl = aggregate(table_name, pk, df, dem)
if "c" in table_name:
pk2 = [x for x in pk]
pk2[pk2.index("course_sc_id")] = df.course_sc_id.str.slice(0, 2)
tbl_course2 = aggregate(table_name, pk2, df, dem, course_flag=True)
tbl = pd.concat([tbl, tbl_course2])
tbl = add_column_length(table_name, tbl)
# tbl.rename(columns={"student_id": "students"}, inplace=True)
file_name = table_name + "_" + dem + ".tsv.bz2" if "d" in table_name else table_name + ".tsv.bz2"
print '''Save {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(os.path.join(output_path, file_name))
tbl.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
def calc_growth(year, current_year_file_path, prev_year_file_path,
prev5_year_file_path):
tbl_name = extract_tbl_name(current_year_file_path)
current_year_tbl = to_df(current_year_file_path, tbl_name)
for prev_path, years_ago in [(prev_year_file_path, 1),
(prev5_year_file_path, 5)]:
if not prev_path: continue
prev_year_tbl = to_df(prev_path, tbl_name)
prev_year_tbl = prev_year_tbl.reset_index(level="year")
prev_year_tbl["year"] = int(year)
prev_year_tbl = prev_year_tbl.set_index("year", append=True)
prev_year_tbl = prev_year_tbl.reorder_levels(
["year"] + list(prev_year_tbl.index.names)[:-1])
current_year_tbl = do_growth(current_year_tbl, prev_year_tbl,
years_ago)
return (tbl_name, current_year_tbl)
def main(file_path, output_path):
# This should create the folder if it's not there yet
if not os.path.exists(output_path):
os.makedirs(output_path)
# Reading the csv, getting a dataframe from pd.read_csv
data_frame = to_df(sys.argv[1])
# Filtering data, where Municipality_ID column = 310620
data_frame = data_frame[(data_frame.Month == 1)]
# Write output
new_file_path = os.path.abspath(os.path.join(output_path, "fout.csv"))
data_frame.to_csv(open(new_file_path, "wb+"), sep=";", index=False, float_format="%.3f", encoding="utf-8")
def main(file_path, output_path):
# This should create the folder if it's not there yet
if not os.path.exists(output_path): os.makedirs(output_path)
# Reading the csv, getting a dataframe from pd.read_csv
data_frame = to_df(sys.argv[1])
# Filtering data, where Municipality_ID column = 310620
data_frame = data_frame[(data_frame.Month == 1)]
# Write output
new_file_path = os.path.abspath(os.path.join(output_path, "fout.csv"))
data_frame.to_csv(open(new_file_path, 'wb+'),
sep=";",
index=False,
float_format="%.3f",
encoding="utf-8")
def main(file_path, year, output_path, prev_path, prev5_path, requireds_only):
print; print "~~~**** YEAR: {0} ****~~~".format(year); print;
start = time.time()
step = 0
# regions state, meso, micro, planning region, munic
depths = {
"bra": [1, 3, 5, 7, 8, 9],
"cnae": [1, 3, 6],
"cbo": [1, 4],
"demo": [1, 4]
}
if file_path:
if not os.path.exists(output_path): os.makedirs(output_path)
d = pd.HDFStore(os.path.join(output_path, 'rais_df_raw.h5'))
if "rais_df" in d:
rais_df = d['rais_df']
else:
step+=1; print; print '''STEP {0}: \nImport file to pandas dataframe'''.format(step)
rais_df = to_df(file_path, False)
try:
d['rais_df'] = rais_df
# d.close()
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
d.close()
os.remove(os.path.join(output_path, 'rais_df_raw.h5'))
# rais_df = to_df(file_path, False)
if "yb" in d and not requireds_only:
tables = {"yb":d["yb"], "yo":d["yo"], "yi":d["yi"], "ybi":d["ybi"], "ybo":d["ybo"], "yio":d["yio"], "ybio":d["ybio"]}
else:
step+=1; print; print '''STEP {0}: \nAggregate'''.format(step)
tables = aggregate(rais_df, depths)
step+=1; print; print 'STEP {0}: \nImportance'.format(step)
tables["yio"] = importance(tables["ybio"], tables["ybi"], tables["yio"], tables["yo"], year, depths)
try:
d["yb"] = tables["yb"]; d["yo"] = tables["yo"]; d["yi"] = tables["yi"]; d["ybi"] = tables["ybi"]; d["ybo"] = tables["ybo"]; d["yio"] = tables["yio"]; d["ybio"] = tables["ybio"]
d.close()
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
d.close()
os.remove(os.path.join(output_path, 'rais_df_raw.h5'))
step+=1; print; print 'STEP {0}: \nRequired'.format(step)
[tables["ybi"], tables["ybio"]] = required(tables["ybio"], tables["ybi"], tables["yi"], year, depths, output_path)
# print tables["ybi"].head()
# sys.exit()
step+=1; print; print 'STEP {0}: \nDiversity'.format(step)
tables["yb"] = calc_diversity(tables["ybi"], tables["yb"], "bra_id", "cnae_id", year, depths)
tables["yb"] = calc_diversity(tables["ybo"], tables["yb"], "bra_id", "cbo_id", year, depths)
tables["yi"] = calc_diversity(tables["ybi"], tables["yi"], "cnae_id", "bra_id", year, depths)
tables["yi"] = calc_diversity(tables["yio"], tables["yi"], "cnae_id", "cbo_id", year, depths)
tables["yo"] = calc_diversity(tables["ybo"], tables["yo"], "cbo_id", "bra_id", year, depths)
tables["yo"] = calc_diversity(tables["yio"], tables["yo"], "cbo_id", "cnae_id", year, depths)
step+=1; print; print 'STEP {0}: \nCalculate RCA, diversity and opportunity gain aka RDO'.format(step)
tables["ybi"] = rdo(tables["ybi"], tables["yi"], year, depths)
for table_name, table_data in tables.items():
table_data = add_column_length(table_name, table_data)
print; print '''FINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
new_file_path = os.path.abspath(os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True, float_format="%.3f")
if prev_path:
print; print '''Calculating growth:'''
for current_year_file_path in findFiles(output_path, '*.tsv.bz2'):
if "growth" in current_year_file_path: continue
current_year_file_name = os.path.basename(current_year_file_path)
prev_year_file_path = os.path.join(prev_path, current_year_file_name)
prev5_year_file_path = None
if prev5_path:
prev5_year_file_path = os.path.join(prev5_path, current_year_file_name)
if not os.path.exists(prev_year_file_path):
print "Unable to find", current_year_file_name, "for previous year."
continue
tbl_name, tbl_w_growth = calc_growth(year, current_year_file_path, prev_year_file_path, prev5_year_file_path)
print tbl_name
new_file_path = os.path.abspath(os.path.join(output_path, "{0}_growth.tsv.bz2".format(tbl_name)))
tbl_w_growth.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True, float_format="%.3f")
# os.remove(current_year_file_path)
print("--- %s minutes ---" % str((time.time() - start)/60))
def main(file_path, trade_flow, year, eci_file_path, pci_file_path, output_path, prev_path, prev5_path):
start = time.time()
step = 0
depths = {
"bra": [1, 3, 5, 7, 8, 9],
"hs": [2, 6],
"wld": [2, 5]
}
step += 1; print '''\nSTEP {0}: \nImport file to pandas dataframe'''.format(step)
secex_df = to_df(file_path, False)
secex_df = secex_df.head(1000)
sys.exit()
step += 1; print '''\nSTEP {0}: \nAggregate'''.format(step)
ybpw = aggregate(secex_df)
step += 1; print '''\nSTEP {0}: \nShard'''.format(step)
[yb, ybp, ybw, yp, ypw, yw] = shard(ybpw, depths)
if trade_flow == "export":
step += 1; print '''\nSTEP {0}: \nCalculate PCI & ECI'''.format(step)
[yp, yw] = pci_wld_eci(eci_file_path, pci_file_path, yp, yw)
step += 1; print '''\nSTEP {0}: \nCalculate domestic ECI'''.format(step)
yb = domestic_eci(yp, yb, ybp, depths)
step += 1; print '''\nSTEP {0}: \nCalculate diversity'''.format(step)
yb = calc_diversity(ybp, yb, "bra_id", "hs_id", depths)
yb = calc_diversity(ybw, yb, "bra_id", "wld_id", depths)
yp = calc_diversity(ybp, yp, "hs_id", "bra_id", depths)
yp = calc_diversity(ypw, yp, "hs_id", "wld_id", depths)
yw = calc_diversity(ybw, yw, "wld_id", "bra_id", depths)
yw = calc_diversity(ypw, yw, "wld_id", "hs_id", depths)
if trade_flow == "export":
step += 1; print '''\nSTEP {0}: \nCalculate Brazilian RCA'''.format(step)
yp = brazil_rca(yp, year)
if trade_flow == "export":
step += 1; print '''\nSTEP {0}: \nCalculate RCA, diversity and opp_gain aka RDO'''.format(step)
ybp = rdo(ybp, yp, year, depths)
if trade_flow == "import":
step += 1; print '''\nSTEP {0}: \nCalculate RCD calculation'''.format(step)
ybp = rcd(ybp, yp, year, depths)
# print ybp.head(20)
# sys.exit()
tables = {"yb": yb, "yp": yp, "yw": yw, "ybp": ybp, "ybpw": ybpw, "ybw": ybw, "ypw": ypw}
if prev_path:
step += 1; print '''\nSTEP {0}: \nCalculate 1 year growth'''.format(step)
if prev5_path:
step += 1; print '''\nSTEP {0}: \nCalculate 5 year growth'''.format(step)
for t_name, t in tables.items():
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] + list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev)
if prev5_path:
prev_file = os.path.join(prev5_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] + list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev, 5)
print "computing column lengths"
for table_name, table_data in tables.items():
tables[table_name] = add_column_length(table_name, table_data)
print '''\nFINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
if not os.path.exists(output_path):
os.makedirs(output_path)
new_file_path = os.path.abspath(os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
total_run_time = (time.time() - start) / 60
print; print;
print "Total runtime: {0} minutes".format(int(total_run_time))
print; print;
def main(file_path, year, output_path):
pre_check()
output_path = os.path.join(output_path, str(year))
print "\nYEAR: {0}\n".format(year)
this_output_path = os.path.join(output_path)
if not os.path.exists(this_output_path): os.makedirs(this_output_path)
step = 0
step+=1; print '''STEP {0}: Import file to pandas dataframe'''.format(step)
df = to_df(file_path, year)
tables_list = ["yb", "ybd", "yd", "ybc", "yc", "ybu", "ybcd", "yu", "yuc", "yucd", "yud"]
pk_lookup = {"y": "year", "d": "d_id", "b": "bra_id", "c": "course_hedu_id", "u": "university_id"}
ybuc = None
for table_name in tables_list:
pk = [pk_lookup[l] for l in table_name]
print "working on", table_name
dems = ['gender', 'ethnicity', 'school_type'] if "d" in table_name else ['']
for dem in dems:
print '''\nSTEP 2: Aggregate {0}'''.format(dem)
tbl = aggregate(pk, df, dem)
if "c" in table_name:
pk2 = [x for x in pk]
pk2[pk2.index("course_hedu_id")] = df.course_hedu_id.str.slice(0, 2)
# df2.course_hedu_id = df.course_hedu_id.str.slice(0, 2)
tbl_course2 = aggregate(pk2, df, dem)
tbl = pd.concat([tbl, tbl_course2])
tbl = add_column_length(table_name, tbl)
tbl.rename(columns={"student_id": "students"}, inplace=True)
if table_name == "yb":
tbl.rename(columns={"university_id": "num_universities"}, inplace=True)
if table_name == "ybuc":
print tbl.head()
ybuc = tbl
file_name = table_name + "_" + dem + ".tsv.bz2" if "d" in table_name else table_name + ".tsv.bz2"
print '''Save {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(os.path.join(output_path, file_name))
tbl.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
# if "c" in table_name:
# print '''\nSTEP 3: Aggregate {0}'''
# tbl = aggregate(pk, df, '', 2)
# tbl = add_column_length(table_name, tbl)
# # print tbl.reset_index().course_hedu_id.nunique()
# file_name = table_name + "_cid2.tsv.bz2"
# print '''Save {0} to output path'''.format(file_name)
# new_file_path = os.path.abspath(os.path.join(output_path, file_name))
# tbl.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
if ybuc is not None:
step+=1; print '''STEP {0}: Calculating RCAs'''.format(step)
ybc = calc_rca(ybuc, year)
new_file_path = os.path.abspath(os.path.join(output_path, "ybc_rca.tsv.bz2"))
ybc.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
print "writing", new_file_path
def main(year, output_path, attr_type):
if "-" in year:
years = range(int(year.split('-')[0]), int(year.split('-')[1]) + 1)
else:
years = [int(year)]
print("years:", str(years))
start = time.time()
for year in years:
d = pd.HDFStore(os.path.join(output_path, str(year), 'rais_df_raw.h5'))
if "rais_df" in d:
rais_df = d['rais_df']
else:
file_path = os.path.join(output_path, 'Rais_{}.csv'.format(year))
rais_df = to_df(file_path)
d['rais_df'] = rais_df
hist_bins = pd.HDFStore(
os.path.join(output_path, '{}_hist_bins.h5'.format(attr_type)))
for depth in depths_lookup[attr_type]:
print("\n{} depth: {}\n".format(attr_type, depth))
this_depth_df = rais_df.copy()
this_depth_df['{}_id'.format(attr_type)] = this_depth_df[
'{}_id'.format(attr_type)].str.slice(0, depth)
# uniqs = ['1112', '8401', '8202', '7842', '7621']:
uniqs = this_depth_df["{}_id".format(attr_type)].unique()
for i, id in enumerate(uniqs):
this_id_df = this_depth_df[this_depth_df['{}_id'.format(
attr_type)] == id]
if len(this_id_df.index) < 10:
print("\nNot enough occurences for histogram")
continue
print("********* {}: {} ({}/{}) *********".format(
year, id, i + 1, len(uniqs)),
end='\r')
sys.stdout.flush()
if int(year) == latest_year:
wage = this_id_df["wage"]
wmin = rounddown(wage.mean() - (wage.std() * 2))
wmin = 0 if wmin < 0 else wmin
wmax = rounddown(wage.mean() + (wage.std() * 2))
wrange = wmax - wmin
# print wrange
bin_size = 100
if wrange > 3000:
bin_size = 200
if wrange > 5000:
bin_size = 500
if wrange > 10000:
bin_size = 1000
''' !!! exception for regions (all need to have same bins!) !!! '''
if attr_type == "bra" and depth == 1:
bin_size = 200
wmin = 0
wmax = 5200
hist_bins["{}_{}".format(attr_type, id)] = pd.Series(
[wmin, wmax, bin_size])
else:
if "{}_{}".format(attr_type, id) in hist_bins:
wmin, wmax, bin_size = hist_bins["{}_{}".format(
attr_type, id)]
else:
continue
hist(id, this_id_df, wmin, wmax, bin_size, attr_type, year)
d.close()
hist_bins.close()
time_elapsed = "%s minutes" % str((time.time() - start) / 60)
print('''\nTotal time %s''' % time_elapsed)
print('''\nSending alert e-mail''')
client = sendgrid.SendGridClient(os.environ['SENDGRID_API_KEY'])
message = sendgrid.Mail()
message.add_to(os.environ.get('ADMIN_EMAIL', '*****@*****.**'))
message.set_from("*****@*****.**")
message.set_subject("Rais histogram for %s ready!" % year)
message.set_html(
"Your calculation took %s, please check out the output at the calc-server"
% time_elapsed)
client.send(message)
def main(file_path, year, output_path, prev_path, prev5_path):
start = time.time()
step = 0
geo_depths = [2, 4, 6, 7, 8] # state, meso, micro, planning region, munic
d = pd.HDFStore(os.path.abspath(os.path.join(output_path, 'rais.h5')))
step += 1
print
print '''STEP {0}: \nImport file to pandas dataframe'''.format(step)
rais_df = to_df(file_path, False, calc_d_id=True)
step += 1
print
print '''STEP {0}: \nAggregate with Demographics'''.format(step)
tables = aggregate_demographics(rais_df, geo_depths)
for table_name, table_data in tables.items():
table_data = add_column_length(table_name, table_data)
# print table_data.head()
if prev_path:
step += 1
print
print '''STEP {0}: \nCalculate 1 year growth'''.format(step)
for t_name, t in tables.items():
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name, calc_d_id=True)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] +
list(t_prev.index.names)[:-1])
tables[t_name] = calc_growth(t, t_prev)
print tables[t_name].head()
# sys.exit()
if prev5_path:
step += 1
print
print '''STEP {0}: \nCalculate 5 year growth'''.format(step)
prev_file = os.path.join(prev5_path,
"{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name, calc_d_id=True)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] +
list(t_prev.index.names)[:-1])
# t_prev = to_df(prev_file, t_name)
tables[t_name] = calc_growth(tables[t_name], t_prev, 5)
print
print '''FINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
if not os.path.exists(output_path):
os.makedirs(output_path)
new_file_path = os.path.abspath(
os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'),
sep="\t",
index=True,
float_format="%.2f")
print("--- %s minutes ---" % str((time.time() - start) / 60))
import sys
from _to_df import to_df
if len(sys.argv) < 2:
sys.exit("Usage: print.py csv_file.csv")
df = to_df(sys.argv[1])
print df.head()
def main(file_path, year, output_path, prev_path, prev5_path):
print "\nHEDU YEAR: {0}\n".format(year)
pre_check()
output_path = os.path.join(output_path, str(year))
if not os.path.exists(output_path):
os.makedirs(output_path)
hdf_store = pd.HDFStore(
os.path.abspath(os.path.join(output_path, 'hedu_data.h5')))
print '''\nImport file to pandas dataframe'''
if "hedu_df" in hdf_store:
hedu_df = hdf_store['hedu_df']
else:
hedu_df = to_df(file_path, year)
try:
hdf_store['hedu_df'] = hedu_df
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
hdf_store.close()
os.remove(os.path.join(output_path, 'hedu_data.h5'))
tables_list = ["yb", "yu", "yc", "ybc", "ybu", "yuc", "ybuc"]
index_lookup = {
"y": "year",
"b": "bra_id",
"c": "course_hedu_id",
"u": "university_id"
}
for table_name in tables_list:
indexes = [index_lookup[l] for l in table_name]
print '''\nAggregating {0}'''.format(table_name)
aggregated_df = aggregate(indexes, hedu_df)
print '''Adding length column to {0}'''.format(table_name)
aggregated_df = add_column_length(table_name, aggregated_df)
print '''Renaming {0} columns'''.format(table_name)
aggregated_df.rename(columns={"student_id": "students"}, inplace=True)
if 'u' not in table_name:
aggregated_df.rename(columns={"university_id": "num_universities"},
inplace=True)
if prev_path:
print '''\nCalculating {0} 1 year growth'''.format(table_name)
previous_df = open_prev_df(prev_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df,
['enrolled', 'graduates'])
if prev5_path:
print '''\nCalculating {0} 5 year growth'''.format(table_name)
previous_df = open_prev_df(prev5_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df,
['enrolled', 'graduates'], 5)
if table_name == "ybuc":
print '''Calculating RCAs'''
ybc = calc_rca(aggregated_df, year)
new_file_path = os.path.abspath(
os.path.join(output_path, "ybc_rca.tsv.bz2"))
ybc.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
file_name = table_name + ".tsv.bz2"
print '''Save {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(os.path.join(output_path, file_name))
aggregated_df.to_csv(bz2.BZ2File(new_file_path, 'wb'),
sep="\t",
index=True)
def main(file_path, year, output_path, prev_path, prev5_path):
print "\nSC YEAR: {0}\n".format(year)
start = time.time()
pre_check()
output_path = os.path.join(output_path, str(year))
if not os.path.exists(output_path):
os.makedirs(output_path)
hdf_store = pd.HDFStore(
os.path.abspath(os.path.join(output_path, 'sc_data.h5')))
print '''\nImport file to pandas dataframe'''
if "sc_df" in hdf_store:
sc_df = hdf_store['sc_df']
else:
sc_df = to_df(file_path)
try:
hdf_store['sc_df'] = sc_df
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
hdf_store.close()
os.remove(os.path.join(output_path, 'sc_data.h5'))
tables_list = ["yb", "yc", "ys", "ybs", "ybc", "ysc", "ybsc"]
index_lookup = {"y": "year", "b": "bra_id", "c": "course_sc_id", "s": "school_id"}
for table_name in tables_list:
indexes = [index_lookup[l] for l in table_name]
print '''\nAggregating {0}'''.format(table_name)
aggregated_df = aggregate(indexes, sc_df)
print '''Adding length column to {0}'''.format(table_name)
aggregated_df = add_column_length(table_name, aggregated_df)
print '''Renaming {0} columns'''.format(table_name)
aggregated_df.rename(columns={"enroll_id": "enrolled"}, inplace=True)
aggregated_df.rename(columns={"class_id": "classes"}, inplace=True)
if 's' not in table_name:
aggregated_df.rename(columns={"school_id": "num_schools"}, inplace=True)
if prev_path:
print '''\nCalculating {0} 1 year growth'''.format(table_name)
previous_df = open_prev_df(prev_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df, ['enrolled'])
if prev5_path:
print '''\nCalculating {0} 5 year growth'''.format(table_name)
previous_df = open_prev_df(prev5_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df, ['enrolled'], 5)
file_name = table_name + ".tsv.bz2"
print '''\nSave {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(os.path.join(output_path, file_name))
aggregated_df.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
time_elapsed = "%s minutes" % str((time.time() - start) / 60)
print '''\nTotal time %s''' % time_elapsed
print '''\nSending alert e-mail'''
client = sendgrid.SendGridClient(os.environ['SENDGRID_API_KEY'])
message = sendgrid.Mail()
message.add_to(os.environ.get('ADMIN_EMAIL', '*****@*****.**'))
message.set_from("*****@*****.**")
message.set_subject("Scholar census %s ready!" % year)
message.set_html("Your calculation took %s, please check out the output at the calc-server" % time_elapsed)
client.send(message)
def main(file_path, year, output_path):
pre_check()
output_path = os.path.join(output_path, str(year))
print "\nYEAR: {0}\n".format(year)
this_output_path = os.path.join(output_path)
if not os.path.exists(this_output_path): os.makedirs(this_output_path)
step = 0
step += 1
print '''STEP {0}: Import file to pandas dataframe'''.format(step)
df = to_df(file_path, year)
tables_list = [
"yb", "ybd", "yd", "ybc", "yc", "ybu", "ybcd", "yu", "yuc", "yucd",
"yud"
]
pk_lookup = {
"y": "year",
"d": "d_id",
"b": "bra_id",
"c": "course_hedu_id",
"u": "university_id"
}
ybuc = None
for table_name in tables_list:
pk = [pk_lookup[l] for l in table_name]
print "working on", table_name
dems = ['gender', 'ethnicity', 'school_type'
] if "d" in table_name else ['']
for dem in dems:
print '''\nSTEP 2: Aggregate {0}'''.format(dem)
tbl = aggregate(pk, df, dem)
if "c" in table_name:
pk2 = [x for x in pk]
pk2[pk2.index("course_hedu_id")] = df.course_hedu_id.str.slice(
0, 2)
# df2.course_hedu_id = df.course_hedu_id.str.slice(0, 2)
tbl_course2 = aggregate(pk2, df, dem)
tbl = pd.concat([tbl, tbl_course2])
tbl = add_column_length(table_name, tbl)
tbl.rename(columns={"student_id": "students"}, inplace=True)
if table_name == "yb":
tbl.rename(columns={"university_id": "num_universities"},
inplace=True)
if table_name == "ybuc":
print tbl.head()
ybuc = tbl
file_name = table_name + "_" + dem + ".tsv.bz2" if "d" in table_name else table_name + ".tsv.bz2"
print '''Save {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(
os.path.join(output_path, file_name))
tbl.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
# if "c" in table_name:
# print '''\nSTEP 3: Aggregate {0}'''
# tbl = aggregate(pk, df, '', 2)
# tbl = add_column_length(table_name, tbl)
# # print tbl.reset_index().course_hedu_id.nunique()
# file_name = table_name + "_cid2.tsv.bz2"
# print '''Save {0} to output path'''.format(file_name)
# new_file_path = os.path.abspath(os.path.join(output_path, file_name))
# tbl.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
if ybuc is not None:
step += 1
print '''STEP {0}: Calculating RCAs'''.format(step)
ybc = calc_rca(ybuc, year)
new_file_path = os.path.abspath(
os.path.join(output_path, "ybc_rca.tsv.bz2"))
ybc.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
print "writing", new_file_path
def main(file_path, year, output_path, prev_path, prev5_path):
print "\nSC YEAR: {0}\n".format(year)
start = time.time()
pre_check()
output_path = os.path.join(output_path, str(year))
if not os.path.exists(output_path):
os.makedirs(output_path)
hdf_store = pd.HDFStore(
os.path.abspath(os.path.join(output_path, 'sc_data.h5')))
print '''\nImport file to pandas dataframe'''
if "sc_df" in hdf_store:
sc_df = hdf_store['sc_df']
else:
sc_df = to_df(file_path)
try:
hdf_store['sc_df'] = sc_df
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
hdf_store.close()
os.remove(os.path.join(output_path, 'sc_data.h5'))
tables_list = ["yb", "yc", "ys", "ybs", "ybc", "ysc", "ybsc"]
index_lookup = {
"y": "year",
"b": "bra_id",
"c": "course_sc_id",
"s": "school_id"
}
for table_name in tables_list:
indexes = [index_lookup[l] for l in table_name]
print '''\nAggregating {0}'''.format(table_name)
aggregated_df = aggregate(indexes, sc_df)
print '''Adding length column to {0}'''.format(table_name)
aggregated_df = add_column_length(table_name, aggregated_df)
print '''Renaming {0} columns'''.format(table_name)
aggregated_df.rename(columns={"enroll_id": "enrolled"}, inplace=True)
aggregated_df.rename(columns={"class_id": "classes"}, inplace=True)
if 's' not in table_name:
aggregated_df.rename(columns={"school_id": "num_schools"},
inplace=True)
if prev_path:
print '''\nCalculating {0} 1 year growth'''.format(table_name)
previous_df = open_prev_df(prev_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df,
['enrolled'])
if prev5_path:
print '''\nCalculating {0} 5 year growth'''.format(table_name)
previous_df = open_prev_df(prev5_path, table_name, year, indexes)
aggregated_df = calc_growth(aggregated_df, previous_df,
['enrolled'], 5)
file_name = table_name + ".tsv.bz2"
print '''\nSave {0} to output path'''.format(file_name)
new_file_path = os.path.abspath(os.path.join(output_path, file_name))
aggregated_df.to_csv(bz2.BZ2File(new_file_path, 'wb'),
sep="\t",
index=True)
time_elapsed = "%s minutes" % str((time.time() - start) / 60)
print '''\nTotal time %s''' % time_elapsed
print '''\nSending alert e-mail'''
client = sendgrid.SendGridClient(os.environ['SENDGRID_API_KEY'])
message = sendgrid.Mail()
message.add_to(os.environ.get('ADMIN_EMAIL', '*****@*****.**'))
message.set_from("*****@*****.**")
message.set_subject("Scholar census %s ready!" % year)
message.set_html(
"Your calculation took %s, please check out the output at the calc-server"
% time_elapsed)
client.send(message)
def main(export_file_path, import_file_path, year, eci_file_path,
pci_file_path, ypw_file_path, output_path, prev_path, prev5_path):
output_path = os.path.join(output_path, str(year))
start = time.time()
step = 0
depths = {"bra": [1, 3, 5, 7, 9], "hs": [2, 6], "wld": [2, 5]}
if not os.path.exists(output_path):
os.makedirs(output_path)
d = pd.HDFStore(os.path.join(output_path, 'secex.h5'))
# if "ymb" in d:
if "ymbp" in d:
tables = {}
tables["ymb"] = d["ymb"]
tables["ymp"] = d["ymp"]
tables["ymw"] = d["ymw"]
tables["ymbp"] = d["ymbp"]
tables["ymbw"] = d["ymbw"]
tables["ympw"] = d["ympw"]
tables["ymbpw"] = d["ymbpw"]
else:
step += 1
print '''\nSTEP {0}: \nImport file to pandas dataframe'''.format(step)
secex_exports = to_df(export_file_path, False)
secex_imports = to_df(import_file_path, False)
step += 1
print '''\nSTEP {0}: \nMerge imports and exports'''.format(step)
secex_df = merge(secex_exports, secex_imports)
step += 1
print '''\nSTEP {0}: \nAggregate'''.format(step)
ymbpw = aggregate(secex_df)
step += 1
print '''\nSTEP {0}: \nShard'''.format(step)
[ymb, ymbp, ymbw, ymp, ympw, ymw] = shard(ymbpw)
step += 1
print '''\nSTEP {0}: \nCalculate PCI & ECI'''.format(step)
[ymp, ymw] = pci_wld_eci(eci_file_path, pci_file_path, ymp, ymw, year)
step += 1
print '''\nSTEP {0}: \nCalculate diversity'''.format(step)
ymb = calc_diversity(ymbp, ymb, "bra_id", "hs_id")
ymb = calc_diversity(ymbw, ymb, "bra_id", "wld_id")
ymp = calc_diversity(ymbp, ymp, "hs_id", "bra_id")
ymp = calc_diversity(ympw, ymp, "hs_id", "wld_id")
ymw = calc_diversity(ymbw, ymw, "wld_id", "bra_id")
ymw = calc_diversity(ympw, ymw, "wld_id", "hs_id")
step += 1
print '''\nSTEP {0}: \nCalculate domestic ECI'''.format(step)
ymb = domestic_eci(ymp, ymb, ymbp, depths["bra"])
step += 1
print '''\nSTEP {0}: \nCalculate domestic ECI'''.format(step)
ymb = domestic_eci(ymp, ymb, ymbp, depths["bra"])
step += 1
print '''\nSTEP {0}: \nCalculate Brazilian RCA'''.format(step)
ymp = brazil_rca(ymp, ypw_file_path, year)
step += 1
print '''\nSTEP {0}: \nCalculate RCA, diversity and opp_gain aka RDO'''.format(
step)
ymbp = rdo(ymbp, ymp, year, depths["bra"], ypw_file_path)
tables = {
"ymb": ymb,
"ymp": ymp,
"ymw": ymw,
"ymbp": ymbp,
"ymbpw": ymbpw,
"ymbw": ymbw,
"ympw": ympw
}
for tbln, tbl in tables.items():
d[tbln] = tbl
if prev_path:
step += 1
print '''\nSTEP {0}: \nCalculate 1 year growth'''.format(step)
if prev5_path:
step += 1
print '''\nSTEP {0}: \nCalculate 5 year growth'''.format(step)
for t_name, t in tables.items():
print t_name
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] +
list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev)
if prev5_path:
prev_file = os.path.join(prev5_path,
"{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] +
list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev, 5)
print "computing column lengths"
for table_name, table_data in tables.items():
tables[table_name] = add_column_length(table_name, table_data)
print '''\nFINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
if not os.path.exists(output_path):
os.makedirs(output_path)
new_file_path = os.path.abspath(
os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
total_run_time = (time.time() - start) / 60
print
print
print "Total runtime: {0} minutes".format(int(total_run_time))
print
print
def main(file_path, year, output_path, prev_path, prev5_path, requireds_only):
print
print "~~~**** YEAR: {0} ****~~~".format(year)
print
start = time.time()
step = 0
# regions state, meso, micro, planning region, munic
depths = {
"bra": [1, 3, 5, 7, 8, 9],
"cnae": [1, 3, 6],
"cbo": [1, 4],
"demo": [1, 4]
}
if file_path:
if not os.path.exists(output_path): os.makedirs(output_path)
d = pd.HDFStore(os.path.join(output_path, 'rais_df_raw.h5'))
if "rais_df" in d:
rais_df = d['rais_df']
else:
step += 1
print
print '''STEP {0}: \nImport file to pandas dataframe'''.format(
step)
rais_df = to_df(file_path, False)
try:
d['rais_df'] = rais_df
# d.close()
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
d.close()
os.remove(os.path.join(output_path, 'rais_df_raw.h5'))
# rais_df = to_df(file_path, False)
if "yb" in d and not requireds_only:
tables = {
"yb": d["yb"],
"yo": d["yo"],
"yi": d["yi"],
"ybi": d["ybi"],
"ybo": d["ybo"],
"yio": d["yio"],
"ybio": d["ybio"]
}
else:
step += 1
print
print '''STEP {0}: \nAggregate'''.format(step)
tables = aggregate(rais_df, depths)
step += 1
print
print 'STEP {0}: \nImportance'.format(step)
tables["yio"] = importance(tables["ybio"], tables["ybi"],
tables["yio"], tables["yo"], year,
depths)
try:
d["yb"] = tables["yb"]
d["yo"] = tables["yo"]
d["yi"] = tables["yi"]
d["ybi"] = tables["ybi"]
d["ybo"] = tables["ybo"]
d["yio"] = tables["yio"]
d["ybio"] = tables["ybio"]
d.close()
except OverflowError:
print "WARNING: Unable to save dataframe, Overflow Error."
d.close()
os.remove(os.path.join(output_path, 'rais_df_raw.h5'))
step += 1
print
print 'STEP {0}: \nRequired'.format(step)
[tables["ybi"],
tables["ybio"]] = required(tables["ybio"], tables["ybi"],
tables["yi"], year, depths, output_path)
# print tables["ybi"].head()
# sys.exit()
step += 1
print
print 'STEP {0}: \nDiversity'.format(step)
tables["yb"] = calc_diversity(tables["ybi"], tables["yb"], "bra_id",
"cnae_id", year, depths)
tables["yb"] = calc_diversity(tables["ybo"], tables["yb"], "bra_id",
"cbo_id", year, depths)
tables["yi"] = calc_diversity(tables["ybi"], tables["yi"], "cnae_id",
"bra_id", year, depths)
tables["yi"] = calc_diversity(tables["yio"], tables["yi"], "cnae_id",
"cbo_id", year, depths)
tables["yo"] = calc_diversity(tables["ybo"], tables["yo"], "cbo_id",
"bra_id", year, depths)
tables["yo"] = calc_diversity(tables["yio"], tables["yo"], "cbo_id",
"cnae_id", year, depths)
step += 1
print
print 'STEP {0}: \nCalculate RCA, diversity and opportunity gain aka RDO'.format(
step)
tables["ybi"] = rdo(tables["ybi"], tables["yi"], year, depths)
for table_name, table_data in tables.items():
table_data = add_column_length(table_name, table_data)
print
print '''FINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
new_file_path = os.path.abspath(
os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'),
sep="\t",
index=True,
float_format="%.3f")
if prev_path:
print
print '''Calculating growth:'''
for current_year_file_path in findFiles(output_path, '*.tsv.bz2'):
if "growth" in current_year_file_path: continue
current_year_file_name = os.path.basename(current_year_file_path)
prev_year_file_path = os.path.join(prev_path,
current_year_file_name)
prev5_year_file_path = None
if prev5_path:
prev5_year_file_path = os.path.join(prev5_path,
current_year_file_name)
if not os.path.exists(prev_year_file_path):
print "Unable to find", current_year_file_name, "for previous year."
continue
tbl_name, tbl_w_growth = calc_growth(year, current_year_file_path,
prev_year_file_path,
prev5_year_file_path)
print tbl_name
new_file_path = os.path.abspath(
os.path.join(output_path,
"{0}_growth.tsv.bz2".format(tbl_name)))
tbl_w_growth.to_csv(bz2.BZ2File(new_file_path, 'wb'),
sep="\t",
index=True,
float_format="%.3f")
# os.remove(current_year_file_path)
print("--- %s minutes ---" % str((time.time() - start) / 60))
def main(output_path, start_from):
start = time.time()
print "Reading rais_df_raw.h5..."
if not os.path.exists(output_path): os.makedirs(output_path)
d = pd.HDFStore(os.path.join(output_path, 'rais_df_raw.h5'))
if "rais_df" in d:
rais_df = d['rais_df']
else:
file_path = raw_input('No rais_df_raw.h5 found, raw file path: ')
rais_df = to_df(file_path, False)
d.close()
year = int(rais_df["year"].unique().tolist()[0])
rais_df = rais_df.drop(["year", "age", "color", "gender", "literacy", "d_id"], axis=1)
cnaes = set(rais_df.cnae_id.unique())
cnaes = cnaes.union({c[:3] for c in cnaes})
cnaes = cnaes.union({c[:1] for c in cnaes})
cnaes = list(cnaes)
cnaes.sort()
if start_from:
cnaes = cnaes[cnaes.index(start_from):]
last_seen = {d:{"id":None, "data":None} for d in depths["cnae"][:-1]}
for i, cnae in enumerate(cnaes):
s = time.time()
prev_id_len = depths["cnae"].index(len(cnae))-1
prev_id_len = depths["cnae"][prev_id_len]
if prev_id_len in last_seen and cnae[:prev_id_len] == last_seen[prev_id_len]["id"]:
cnae_df = last_seen[prev_id_len]["data"][last_seen[prev_id_len]["data"].cnae_id.str.startswith(cnae)]
else:
cnae_df = rais_df[rais_df.cnae_id.str.startswith(cnae)]
if len(cnae) in last_seen:
last_seen[len(cnae)]["id"] = cnae
last_seen[len(cnae)]["data"] = cnae_df.copy()
cnae_df = cnae_df[cnae_df.cnae_id.str.startswith(cnae)]
if len(cnae) < 6:
cnae_df["cnae_id"] = cnae_df["cnae_id"].str.slice(0, len(cnae))
cnae_df = cnae_df[cnae_df["cnae_id"]==cnae]
# cnae_df['est_id'] = cnae_df['est_id'].str.cat(cnae_df['est_size'].values.astype(str), sep='_')
# cnae_df = cnae_df.drop(["est_size"], axis=1)
ests = cnae_df.groupby(["est_size", "est_id"]).agg({"wage":pd.Series.median})
bounds_lower = ests.groupby(level=["est_size"]).agg({"wage":lambda x: x.quantile(0.25)})
bounds_upper = ests.groupby(level=["est_size"]).agg({"wage":lambda x: x.quantile(0.75)})
ests = ests.reset_index(level=["est_id"])
ests["lower"] = bounds_lower["wage"]
ests["upper"] = bounds_upper["wage"]
# print ests.shape
ests = ests[(ests["wage"]>=ests["lower"]) & (ests["wage"]<=ests["upper"])]
# print ests.shape
# print ests["est_id"].count(), ests["est_id"].nunique()
# cnae_df["est_qualify"] = cnae_df["est_id"].apply(lambda x: x in ests["est_id"].tolist())
# cnae_df = cnae_df[cnae_df["est_qualify"]]
cnae_df = cnae_df[cnae_df["est_id"].isin(ests["est_id"])]
if cnae_df.empty: continue
num_ests = ests.groupby(level=0).agg({"est_id":pd.Series.count})
# cbos = cnae_df.groupby(["est_size", "cbo_id"]).agg({"est_id":lambda x: set.union(set(x)), "num_emp":pd.Series.count, "wage":pd.Series.median})
cbos = cnae_df.groupby(["est_size", "cbo_id"]).agg({"est_id": pd.Series.nunique, "num_emp":pd.Series.count, "wage":pd.Series.median})
cbos = cbos.reset_index(level=["cbo_id"])
# cbos['test'] = cbos.est_id.str.len()
cbos['num_est'] = num_ests["est_id"]
cbos['qualify'] = cbos["est_id"] / cbos["num_est"]
cbos = cbos[cbos['qualify'] >= 0.2]
cbos["ene"] = cbos["num_emp"] / cbos["est_id"]
cbos = cbos.reset_index().set_index(["cbo_id", "est_size"])
# print cbos["ene"].head()
ene = cbos["ene"].unstack(level=-1)
ene = ene.rename(columns={0:'ene_micro', 1:'ene_small', 2:'ene_medium', 3:'ene_large'})
ene["cnae_id"] = cnae
ene["year"] = year
ene = ene.set_index(["year", "cnae_id"], append=True)
ene = ene.reorder_levels(["year", "cnae_id", "cbo_id"])
print cnae, (time.time() - s) / 60
fname_yio = os.path.join(output_path, 'ene.csv')
if i == 0 and not start_from:
ene.to_csv(fname_yio)
else:
ene.to_csv(open(fname_yio, 'a'), header=False)
print "Done! Merging..."
index_col = ["year", "cnae_id", "cbo_id"]
full_tbl = pd.read_csv(os.path.join(output_path, "yio.tsv.bz2"), sep="\t", compression="bz2", converters={"cbo_id":str, "cnae_id":str, "year":int})
full_tbl = full_tbl.set_index(index_col)
ene_tbl = pd.read_csv(os.path.join(output_path, "ene.csv"), converters={"cbo_id":str, "cnae_id":str, "year":int})
ene_tbl = ene_tbl.set_index(index_col)
full_tbl = full_tbl.join(ene_tbl, how='outer')
new_file_path = os.path.abspath(os.path.join(output_path, "yio_ene.tsv.bz2"))
full_tbl.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True, float_format="%.2f")
print("--- %s minutes ---" % str((time.time() - start)/60))
def main(file_path, trade_flow, year, eci_file_path, pci_file_path,
output_path, prev_path, prev5_path):
start = time.time()
step = 0
depths = {"bra": [1, 3, 5, 7, 8, 9], "hs": [2, 6], "wld": [2, 5]}
step += 1
print '''\nSTEP {0}: \nImport file to pandas dataframe'''.format(step)
secex_df = to_df(file_path, False)
secex_df = secex_df.head(1000)
sys.exit()
step += 1
print '''\nSTEP {0}: \nAggregate'''.format(step)
ybpw = aggregate(secex_df)
step += 1
print '''\nSTEP {0}: \nShard'''.format(step)
[yb, ybp, ybw, yp, ypw, yw] = shard(ybpw, depths)
if trade_flow == "export":
step += 1
print '''\nSTEP {0}: \nCalculate PCI & ECI'''.format(step)
[yp, yw] = pci_wld_eci(eci_file_path, pci_file_path, yp, yw)
step += 1
print '''\nSTEP {0}: \nCalculate domestic ECI'''.format(step)
yb = domestic_eci(yp, yb, ybp, depths)
step += 1
print '''\nSTEP {0}: \nCalculate diversity'''.format(step)
yb = calc_diversity(ybp, yb, "bra_id", "hs_id", depths)
yb = calc_diversity(ybw, yb, "bra_id", "wld_id", depths)
yp = calc_diversity(ybp, yp, "hs_id", "bra_id", depths)
yp = calc_diversity(ypw, yp, "hs_id", "wld_id", depths)
yw = calc_diversity(ybw, yw, "wld_id", "bra_id", depths)
yw = calc_diversity(ypw, yw, "wld_id", "hs_id", depths)
if trade_flow == "export":
step += 1
print '''\nSTEP {0}: \nCalculate Brazilian RCA'''.format(step)
yp = brazil_rca(yp, year)
if trade_flow == "export":
step += 1
print '''\nSTEP {0}: \nCalculate RCA, diversity and opp_gain aka RDO'''.format(
step)
ybp = rdo(ybp, yp, year, depths)
if trade_flow == "import":
step += 1
print '''\nSTEP {0}: \nCalculate RCD calculation'''.format(step)
ybp = rcd(ybp, yp, year, depths)
# print ybp.head(20)
# sys.exit()
tables = {
"yb": yb,
"yp": yp,
"yw": yw,
"ybp": ybp,
"ybpw": ybpw,
"ybw": ybw,
"ypw": ypw
}
if prev_path:
step += 1
print '''\nSTEP {0}: \nCalculate 1 year growth'''.format(step)
if prev5_path:
step += 1
print '''\nSTEP {0}: \nCalculate 5 year growth'''.format(step)
for t_name, t in tables.items():
prev_file = os.path.join(prev_path, "{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] +
list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev)
if prev5_path:
prev_file = os.path.join(prev5_path,
"{0}.tsv.bz2".format(t_name))
t_prev = to_df(prev_file, t_name)
t_prev = t_prev.reset_index(level="year")
t_prev["year"] = int(year)
t_prev = t_prev.set_index("year", append=True)
t_prev = t_prev.reorder_levels(["year"] +
list(t_prev.index.names)[:-1])
t = calc_growth(t, t_prev, 5)
print "computing column lengths"
for table_name, table_data in tables.items():
tables[table_name] = add_column_length(table_name, table_data)
print '''\nFINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
if not os.path.exists(output_path):
os.makedirs(output_path)
new_file_path = os.path.abspath(
os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
total_run_time = (time.time() - start) / 60
print
print
print "Total runtime: {0} minutes".format(int(total_run_time))
print
print
def main(export_file_path, import_file_path, year, eci_file_path, pci_file_path, ypw_file_path, output_path):
start = time.time()
step = 0
depths = {
"bra": [1, 3, 5, 7, 9],
"hs": [2, 6],
"wld": [2, 5]
}
if not os.path.exists(output_path): os.makedirs(output_path)
d = pd.HDFStore(os.path.join(output_path, 'secex.h5'))
# if "ymb" in d:
if "ymbp" in d:
tables = {}
tables["ymb"] = d["ymb"]; tables["ymp"] = d["ymp"]; tables["ymw"] = d["ymw"]; tables["ymbp"] = d["ymbp"]; tables["ymbw"] = d["ymbw"]; tables["ympw"] = d["ympw"]; tables["ymbpw"] = d["ymbpw"]
else:
step += 1; print '''\nSTEP {0}: \nImport file to pandas dataframe'''.format(step)
secex_exports = to_df(export_file_path, False)
secex_imports = to_df(import_file_path, False)
# secex_exports = secex_exports.head(1000)
# secex_imports = secex_imports.head(1000)
step += 1; print '''\nSTEP {0}: \nMerge imports and exports'''.format(step)
secex_df = merge(secex_exports, secex_imports)
step += 1; print '''\nSTEP {0}: \nAggregate'''.format(step)
ymbpw = aggregate(secex_df)
step += 1; print '''\nSTEP {0}: \nShard'''.format(step)
[ymb, ymbp, ymbw, ymp, ympw, ymw] = shard(ymbpw)
step += 1; print '''\nSTEP {0}: \nCalculate PCI & ECI'''.format(step)
[ymp, ymw] = pci_wld_eci(eci_file_path, pci_file_path, ymp, ymw, year)
step += 1; print '''\nSTEP {0}: \nCalculate diversity'''.format(step)
ymb = calc_diversity(ymbp, ymb, "bra_id", "hs_id")
ymb = calc_diversity(ymbw, ymb, "bra_id", "wld_id")
ymp = calc_diversity(ymbp, ymp, "hs_id", "bra_id")
ymp = calc_diversity(ympw, ymp, "hs_id", "wld_id")
ymw = calc_diversity(ymbw, ymw, "wld_id", "bra_id")
ymw = calc_diversity(ympw, ymw, "wld_id", "hs_id")
step += 1; print '''\nSTEP {0}: \nCalculate domestic ECI'''.format(step)
ymb = domestic_eci(ymp, ymb, ymbp, depths["bra"])
step += 1; print '''\nSTEP {0}: \nCalculate Brazilian RCA'''.format(step)
ymp = brazil_rca(ymp, ypw_file_path, year)
step += 1; print '''\nSTEP {0}: \nCalculate RCA, diversity and opp_gain aka RDO'''.format(step)
ymbp = rdo(ymbp, ymp, year, depths["bra"], ypw_file_path)
tables = {"ymb": ymb, "ymp": ymp, "ymw": ymw, "ymbp": ymbp, "ymbpw": ymbpw, "ymbw": ymbw, "ympw": ympw}
for tbln, tbl in tables.items():
d[tbln] = tbl
print "computing column lengths"
for table_name, table_data in tables.items():
tables[table_name] = add_column_length(table_name, table_data)
print '''\nFINAL STEP: \nSave files to output path'''
for t_name, t in tables.items():
if not os.path.exists(output_path):
os.makedirs(output_path)
new_file_path = os.path.abspath(os.path.join(output_path, "{0}.tsv.bz2".format(t_name)))
t.to_csv(bz2.BZ2File(new_file_path, 'wb'), sep="\t", index=True)
total_run_time = (time.time() - start) / 60
print; print;
print "Total runtime: {0} minutes".format(int(total_run_time))
print; print;