def break_up_jobs_file(self):
#Anon analysis tool reports seem to fail if there's more than 4 or 5k jobs
#splitting up jobs between queries
jobs_list = []
job_file = files.FileHandler()
file_count = 1
row_count = 0
for row in job_file.open_csv(self.automated_files +
"Current Jobs.csv"):
row_count += 1
for i, row in enumerate(
job_file.open_csv(self.automated_files + "Current Jobs.csv")):
main_job = row[job_file.header.index("ANSWER VALUE")]
jobs_list.append(main_job)
if (i % 3000 == 0 and i != 0) or i == row_count - 1:
with open(
self.automated_files + "Current Jobs_" +
str(file_count) + ".csv", 'wb') as W:
writer = csv.writer(W, delimiter=',')
header = "ANSWER VALUE", ""
writer.writerow(header)
for job in jobs_list:
final_job = job, ""
writer.writerow(final_job)
file_count += 1
jobs_list = []
def gather_data(self):
logs = li.CSVLogIterator(self.start_date, self.current_date)
logs.find_all_logs_survey()
file_run = sorted(logs.log_files_to_use)
handler = fw.FileHandler()
for files in file_run:
try:
print "Working on " + files
for row in handler.open_csv(log_file_path + files):
try:
final_job = row[handler.header.index("Profile job")]
unprompted_1 = row[handler.header.index(
'Profile job.unprompted')]
unprompted_2 = row[handler.header.index(
'Job\Job Unprompted')]
final_unprompted = self.determine_unprompted(
unprompted_1, unprompted_2)
combined = final_job, final_unprompted
if "" not in combined:
self.overall_list.append(combined)
self.individual_list.append(final_job)
self.individual_list.append(final_unprompted)
except ValueError:
continue
except IOError:
continue
print "File data completely gathered"
def soc_code_map():
onet_mapping = {}
main_file = fw.FileHandler()
for row in main_file.open_csv(auto_path + "CFM.csv"):
job = row[main_file.header.index("All Confirmed Job Titles")]
soc = row[main_file.header.index("SOC Code")]
onet_mapping[job] = soc
return onet_mapping
def extract_data(self):
print "Unzipping and modifying Analysis Tool results..."
fw.FileHandler().zip_file_open('Ryan Job Rollup Suggestor EAC.zip',
self.temp_out_files)
extract.ExtractXMLData(
'Ryan Job Rollup Suggestor EAC_0.xml').fix_xml_encoding(
self.temp_out_files)
count_dict = extract.ExtractXMLData(self.temp_out_files + 'Ryan Job Rollup Suggestor EAC_0.xml')\
.overall_medians_list_return()
return count_dict
def temp_pull_current_jobs(self):
job_list = []
reader = files.FileHandler()
for row in reader.open_csv(self.automated_files + "Current Jobs.csv"):
job_title = row[reader.header.index("ANSWER VALUE")]
if job_title != "":
job_list.append(job_title)
return list(set(job_list))
def pull_all_current_job_rollups(self):
rollup_list = []
reader = files.FileHandler()
for row in reader.open_tsv(self.automated_files +
"Current Job Rollups.tsv"):
rollup = row[reader.header.index("Read-only Answervalue")]
if rollup != "":
rollup_list.append(rollup)
return list(set(rollup_list))
def create_full_task_dictionary(self):
print "Gathering all tasks into a job to task dictionary..."
handler = files.FileHandler()
task_dict = {}
for line in handler.open_csv(self.automated_files +
'Current Tasks.csv'):
job = line[handler.header.index("JOB")]
tasks = line[handler.header.index("TASK")]
try:
task_dict[job] += " " + tasks.lower()
except KeyError:
task_dict[job] = tasks.lower()
return task_dict
def pull_all_current_jobs(self):
"""This is not currently working. Something is wrong on the C# code side me thinks"""
job_list = []
reader = files.FileHandler()
for row in reader.open_tsv(self.automated_files + "Current Jobs.tsv"):
try:
job_title = row[reader.header.index("ANSWER VALUE")]
if job_title != "":
job_list.append(job_title)
except IndexError:
print row
return list(set(job_list))
def find_breadth_x_soc_codes(self, x):
main_file = fw.FileHandler()
if x == '30':
breadth = 'All Breadth 30'
elif x == '40':
breadth = 'All Breadth 40'
elif x == '50':
breadth = 'All Breadth 50'
else:
breadth = 'All Breadth 60'
soc_list = []
for row in main_file.open_csv(self.main_file_path +
"Onet_Breadths.csv"):
soc = row[main_file.header.index(breadth)]
soc_list.append(soc)
return list(set(soc_list))
def unprompted_pull(self):
matching_list = []
append = matching_list.append
print "Sorting through the unprompted strings file"
handler = fw.FileHandler()
for row in handler.open_csv(unprompted_path + self.current_unprompted):
unprompted = row[1]
confirmed = row[0]
mutual_information = row[5]
word_similarity = row[6]
all = unprompted, confirmed, mutual_information, word_similarity
if float(mutual_information) > 12 and float(word_similarity) < .9:
append(all)
else:
continue
return matching_list
return jaccard
print "Gathering probabilities..."
combo_probs = {}
with open("C:\\users\\ryanm\\desktop\\ProbabilityCache.csv", 'rb') as R:
reader = csv.reader(R, delimiter=',')
header = reader.next()
for row in reader:
combo = row[0].lower(), row[1].lower()
combo_probs[combo] = row[2]
write_header = True
handler = fw.FileHandler()
row_count = 0
with open(
"C:\\users\\ryanm\\desktop\\truth_data_with_basesalary_comparisons_and_prob.csv",
'wb') as W:
writer = csv.writer(W, lineterminator='\n')
for line in handler.open_csv(
"C:\\users\\ryanm\\desktop\\truth_data_with_basesalary_comparisons.csv"
):
row_count += 1
if row_count % 1000 == 0:
print "Processed %s rows..." % row_count
if write_header is True:
def unzip_file(self, zip_file, out_file=None):
if out_file == None:
files.FileHandler().zip_file_open(zip_file, self.out_files)
else:
files.FileHandler().zip_file_open(zip_file, out_file)
