def get_recommendations(keywords):
df = pd.read_csv('richCityData.csv')
score_dict = {}
for index, row in df.iterrows():
score_dict[index] = CosineSimilarity.cosine_similarity_of(row['description'], keywords)
#sort cities by score and index.
sorted_scores = sorted(score_dict.items(), key=operator.itemgetter(1), reverse=True)
counter = 0
#create an empty results data frame.
resultDF = pd.DataFrame(columns=('city', 'popularity', 'description', 'image'))
#get highest scored 5 cities.
for i in sorted_scores:
print(i[0], i[1])
resultDF = resultDF.append({'city': df.iloc[i[0]]['city'], 'popularity': df.iloc[i[0]]['popularity'], 'description': df.iloc[i[0]]['description'], 'image': df.iloc[i[0]]['image']}, ignore_index=True)
counter += 1
if counter>4:
break
#convert DF to json.
json_result = json.dumps(resultDF.to_dict('records'))
return json_result
def test_cosine_similarity_same(self):
text1 = "happy birthday"
text2 = "happy birthday"
cs = CosineSimilarity.cosine_similarity_of(text1, text2)
#strings used due to floating number problem.
self.assertEqual("%.2f" % cs, "1.00")
def test_cosine_similarity_different(self):
text1 = "hello sir"
text2 = "good afternoon"
cs = CosineSimilarity.cosine_similarity_of(text1, text2)
#strings used due to floating number problem.
self.assertEqual("%.2f" % cs, "0.00")
def get_recommendations_include_rating_count_threshold_positive_negative_reviews(
keywords):
df = pd.read_csv('city_data_cleared.csv')
score_dict = {}
for index, row in df.iterrows():
cs_score = CosineSimilarity.cosine_similarity_of(
row['description'], keywords)
rating = row['rating']
rating_count = row['rating_count']
positive_review_count = row['positive_review']
negative_review_count = row['negative_review']
rating_contribution = RatingExtractor.get_rating_weight_with_count_and_reviews(
rating, rating_count, positive_review_count,
negative_review_count)
final_score = RecommenderEngine.calculate_final_score(
cs_score, rating_contribution)
score_dict[index] = final_score
#sort cities by score and index.
sorted_scores = sorted(score_dict.items(),
key=operator.itemgetter(1),
reverse=True)
counter = 0
#create an empty results data frame.
resultDF = pd.DataFrame(columns=('city', 'popularity', 'description',
'score'))
#get highest scored 5 cities.
for i in sorted_scores:
#print index and score of the city.
#print(i[0], i[1])
resultDF = resultDF.append(
{
'city': df.iloc[i[0]]['city'],
'popularity': df.iloc[i[0]]['popularity'],
'description': df.iloc[i[0]]['description'],
'score': i[1]
},
ignore_index=True)
counter += 1
if counter > 4:
break
#convert DF to json.
json_result = json.dumps(resultDF.to_dict('records'))
return json_result
def get_recommendations(resume, jobs_df):
score_dict = {}
for index, row in jobs_df.iterrows():
score_dict[index] = CosineSimilarity.cosine_similarity_of(
row['description_cleaned'], resume)
# Sort descriptions by score and index
sorted_scores = sorted(score_dict.items(),
key=operator.itemgetter(1),
reverse=True)
counter = 0
# Create results data frame
resultDF = pd.DataFrame(columns=[
'Job Index', 'Company', 'Title', 'Location', 'Description',
'Job Description'
]) # , 'score'])
# Get the 10 jobs with the highest similarity scores
for i in sorted_scores:
# print index & score of the job description
resultDF = resultDF.append(
{
'Description': jobs_df.iloc[i[0]]['job_description'],
'Title': jobs_df.iloc[i[0]]['title'],
'Company': jobs_df.iloc[i[0]]['company_name'],
'Location': jobs_df.iloc[i[0]]['location'],
'Job Index': jobs_df.iloc[i[0]]['Unnamed: 0']
},
ignore_index=True)
# 'score': i[1]}, ignore_index=True)
counter += 1
if counter > 10:
break
json_result = json.dumps(resultDF.to_dict('records'))
resultDF.fillna('', inplace=True)
return resultDF
def get_rating_recommendations(keywords):
df = pd.read_csv('ratingRichCityData.csv')
score_dict = {}
for index, row in df.iterrows():
cs = CosineSimilarity.cosine_similarity_of(row['description'], keywords)
rating = row['rating']
rating_count = row['rating_count']
positive_review_count = row['positive_review']
negative_review_count = row['negative_review']
rat_value = RatingExtractor.get_rating_with_count_and_reviews(rating,rating_count,positive_review_count,negative_review_count)
score = RecommenderEngine.calculate_score_from(cs,rat_value)
score_dict[index] = score
sorted_scores = sorted(score_dict.items(), key=operator.itemgetter(1), reverse=True)
counter = 0
resultDF = pd.DataFrame(columns=('city', 'popularity', 'description', 'image'))
#get highest scored 5 cities.
for i in sorted_scores:
print(i[0], i[1])
resultDF = resultDF.append({'city': df.iloc[i[0]]['city'], 'popularity': df.iloc[i[0]]['popularity'], 'description': df.iloc[i[0]]['description'], 'image': df.iloc[i[0]]['image']}, ignore_index=True)
counter += 1
if counter>4:
break
#convert DF to json.
json_result = json.dumps(resultDF.to_dict('records'))
return json_result
def test_cosine_similarity_some(self):
text1 = "apple banana orange"
text2 = "orange berry ananas"
cs = CosineSimilarity.cosine_similarity_of(text1, text2)
self.assertEqual("%.2f" % cs, "0.33")