s444498/fuzzy-logic-movies
1
1
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

api adjusted for changing params

Browse Source
This commit is contained in:
Krystian Wasilewski 2023-01-27 18:43:12 +01:00
parent 2aee4bb263
commit b34f303b02
1 changed files with 46 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

53
main.py
View File

@ -22,13 +22,25 @@ app = FastAPI()
data = pd.DataFrame() data = pd.DataFrame()
mlb = MultiLabelBinarizer() mlb = MultiLabelBinarizer()
def inference(first: pandas.core.series.Series, second_id: str, df=None):
def inference(first: pandas.core.series.Series,
second_id: str,
release_year_param='similar',
runtime_param='similar',
seasons_param='similar',
genres_param='same',
emotions_param='same',
df=None):
if df is not None: if df is not None:
second = df.loc[second_id] second = df.loc[second_id]
else: else:
second = data.loc[second_id] second = data.loc[second_id]
FS = fuzzy_system(release_year_param='similar', runtime_param='similar', seasons_param='similar', genres_param='same', emotions_param='same') FS = fuzzy_system(release_year_param=release_year_param,
runtime_param=runtime_param,
seasons_param=seasons_param,
genres_param=genres_param,
emotions_param=emotions_param)
year_diff = int(first['release_year'] - second['release_year']) year_diff = int(first['release_year'] - second['release_year'])
FS.set_variable('RELEASE_YEAR', year_diff) FS.set_variable('RELEASE_YEAR', year_diff)
@ -51,10 +63,24 @@ def inference(first: pandas.core.series.Series, second_id: str, df=None):
return second_id, FS.inference(['RECOMMENDATION'])['RECOMMENDATION'] return second_id, FS.inference(['RECOMMENDATION'])['RECOMMENDATION']
def process_dataframe(df, production): def process_dataframe(df,
production,
release_year_param,
runtime_param,
seasons_param,
genres_param,
emotions_param
):
scores = [] scores = []
for index, row in df.iterrows(): for index, row in df.iterrows():
scores.append(inference(production, str(index), df)) scores.append(inference(production,
str(index),
release_year_param,
runtime_param,
seasons_param,
genres_param,
emotions_param,
df))
return scores return scores
@ -111,7 +137,13 @@ def rec_score(first_id: str, second_id: str):
@app.get('/recs/{production_id}') @app.get('/recs/{production_id}')
async def recs(production_id: str, count: int | None = 5): async def recs(production_id: str,
release_year_param: str | None = 'similar',
runtime_param: str | None = 'similar',
seasons_param: str | None = 'similar',
genres_param: str | None = 'same',
emotions_param: str | None = 'same',
count: int | None = 5):
try: try:
first = data.loc[production_id] first = data.loc[production_id]
except KeyError: except KeyError:
@ -122,14 +154,21 @@ async def recs(production_id: str, count: int | None = 5):
cpus = multiprocessing.cpu_count() cpus = multiprocessing.cpu_count()
df_list = np.array_split(data, cpus) df_list = np.array_split(data, cpus)
pool = Pool(cpus) pool = Pool(cpus)
results = [pool.apply_async(process_dataframe, [df, first]) for df in df_list] results = [pool.apply_async(process_dataframe,
[df,
first,
release_year_param,
runtime_param,
seasons_param,
genres_param,
emotions_param]) for df in df_list]
for r in results: for r in results:
r.wait() r.wait()
for r in results: for r in results:
scores += r.get() scores += r.get()
print(f'time elapsed = {time.time() - time_start}') print(f'time elapsed = {time.time() - time_start}')
scores = [idx[0] for idx in sorted(scores, key=lambda x: x[1], reverse=True)[:count+1]] scores = [idx[0] for idx in sorted(scores, key=lambda x: x[1], reverse=True)[:count + 1]]
scores.remove(production_id) scores.remove(production_id)
return { return {
'id': scores 'id': scores