loans = csv.DictReader(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/loans_assigned_for_tagging_with_descriptions_new.csv"))
forest = pickle.load(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/Forests/HASForest",
"rb"))
print(forest.best_params_)
vectorizer = pickle.load(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/Vectorizers/HASVectorizer",
"rb"))
selector = pickle.load(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/Selectors/HASSelector",
"rb"))
for loan in tqdm(loans):
if loan["Sector"] == "Health":
continue
modified = [Analysis.modify(loan["Use"])]
if modified != [None]:
modified = vectorizer.transform(modified)
modified_and_selected = selector.transform(modified).toarray()
prediction = forest.predict_proba(modified_and_selected)
if prediction[0][1] < .6: # 0.6
continue
else:
continue
if "#HealthAndSanitation" in loan["Tags"]:
correct += 1
else:
print(total, loan["Raw Link"])
total += 1
print(correct, total)
print(correct / total)
loans = csv.DictReader(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/loans_assigned_for_tagging_with_descriptions.csv"))
pforest = pickle.load(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/Forests/SForest",
"rb"))
pvectorizer = pickle.load(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/Vectorizers/SVectorizer",
"rb"))
pselector = pickle.load(open(
"/Users/thomaswoodside/PycharmProjects/AutoTag/DataFiles/Selectors/SSelector",
"rb"))
for loan in tqdm(loans):
modified = [Analysis.modify(loan["Description"])]
if modified != [None]:
pmodified = pvectorizer.transform(modified)
pmodified_and_selected = pselector.transform(pmodified).toarray()
pprediction = pforest.predict_proba(pmodified_and_selected)
else:
continue
if pprediction[0][1] < 0.5:
continue
if "#Single" in loan["Tags"] or "#SingleParent" in loan["Tags"]:
correct += 1
else:
print(loan["Raw Link"])
total += 1
print(correct, total)
try:
