def search_text(data):
documents, dictionary, lsi, index = load_docs('linkedin', APP_DATA)
sims = query_docs(data, dictionary, lsi, index)
#get 10 best matches
idx = [sims[s][0] for s in range(0, 13)]
results = index_lookup(idx)
# clean results
results = [r for r in results if "Contractor" not in r]
results = [r for r in results if "Intern" not in r]
results = [r for r in results if "Hourly" not in r]
results = [r for r in results if "Monthly" not in r]
results = [r for r in results if "Visiting" not in r]
rtokens = [r.split('/') for r in results]
#results = pull_linkedidx(idx)
clean_res = [{
'Company': r[2],
'Title': r[3].split('.')[0]
} for r in rtokens]
jobs = getSalary(clean_res)
min_sal, max_sal, avg_sal = calc_salary([r['Salary'] for r in jobs])
results = {}
results['status'] = "ok"
results['jobs'] = jobs
results['max_salary'] = '$' + locale.format("%d", max_sal, grouping=True)
results['min_salary'] = '$' + locale.format("%d", min_sal, grouping=True)
results['ave_salary'] = '$' + locale.format("%d", avg_sal, grouping=True)
return results
def search_text(data):
documents, dictionary, lsi, index = load_docs('linkedin',APP_DATA)
sims = query_docs(data, dictionary, lsi, index)
#get 10 best matches
idx = [sims[s][0] for s in range(0,13)]
results = index_lookup(idx)
# clean results
results = [r for r in results if "Contractor" not in r]
results = [r for r in results if "Intern" not in r]
results = [r for r in results if "Hourly" not in r]
results = [r for r in results if "Monthly" not in r]
results = [r for r in results if "Visiting" not in r]
rtokens = [r.split('/') for r in results]
#results = pull_linkedidx(idx)
clean_res = [{'Company':r[2],'Title':r[3].split('.')[0]} for r in rtokens]
jobs = getSalary(clean_res)
min_sal, max_sal, avg_sal = calc_salary([r['Salary'] for r in jobs])
results = {}
results['status'] = "ok"
results['jobs'] = jobs
results['max_salary'] = '$' + locale.format("%d", max_sal, grouping=True)
results['min_salary'] = '$' + locale.format("%d", min_sal, grouping=True)
results['ave_salary'] = '$' + locale.format("%d", avg_sal, grouping=True)
return results
def search_query(url):
data = pull_profile(url)
documents, dictionary, lsi, index = load_docs('linkedin')
sims = query_docs(data, dictionary, lsi, index)
#get 10 best matches
idx = [sims[s][0] for s in range(0,10)]
results = index_lookup(idx)
rtokens = [r.split('/') for r in results]
#results = pull_linkedidx(idx)
clean_res = [{'Company':r[2],'Title':r[3].split('.')[0]} for r in rtokens]
jobs = getSalary(clean_res)
min_sal, max_sal, avg_sal = calc_salary([r['Salary'] for r in jobs])
results = {}
results['jobs'] = jobs
results['max_salary'] = '$' + locale.format("%d", max_sal, grouping=True)
results['min_salary'] = '$' + locale.format("%d", min_sal, grouping=True)
results['ave_salary'] = '$' + locale.format("%d", avg_sal, grouping=True)
return results