def get_bar():
bar = px.bar(cache.get("style_df"), x='style', y='count')
bar.update_layout(title_text='10 Most Frequently Occurring Style Tags',
title_x=0.5,
font_family='Arial')
bar_div = plot(bar, output_type='div')
return bar_div
def get_hm():
df = cache.get("df")
cosine_sim = cache.get("cosine_sim")
hm = px.imshow(cosine_sim * 100,
labels={'color': 'Similarity (%)'},
x=df['release_name'],
y=df['release_name'],
width=800,
height=800)
hm.update_xaxes(showticklabels=False)
hm.update_yaxes(showticklabels=False)
hm.update_layout(
title_text='Heat Map Representing Cosine Similarity Between Albums',
title_x=0.5,
font_family='Arial')
hm_div = plot(hm, output_type='div')
return hm_div
def get_pie():
genre_df = cache.get("genre_df")
pie = px.pie(values=genre_df['count'], names=genre_df.index)
pie.update_layout(title_text='Record Collection Breakdown by Genre',
title_x=0.5,
font_family='Arial')
pie_div = plot(pie, output_type='div')
return pie_div
def get_similar(release_id):
df = cache.get("df")
# Get the df index that corresponds to the release_id argument
idx = cache.get("indices")[release_id]
# Get the release's corresponding artist_id, so we can filter it out of the recommendations
artist_id = df[df['release_id'] == release_id]['artist_id'].iloc[0]
# Get the pairwise similarity scores of all albums against our chosen release
sim_scores = list(enumerate(cache.get("cosine_sim")[idx]))
# Turn that list of tuples into a Pandas series
sim_series = pd.Series([i[1] for i in sim_scores])
sim_series.rename('similarity', inplace=True)
# Merge the series of similarity scores into the DataFrame containing the full collection
similar = df.merge(sim_series,
how='left',
left_index=True,
right_index=True)
# Sort by similariry scores in decending order
similar.sort_values(by=['similarity'], inplace=True, ascending=False)
# Filter out any additional albums by the same artist
similar = similar[similar['artist_id'] != artist_id]
similar.reset_index(drop=True, inplace=True)
i = 1
while i < 9:
if similar.iloc[i].artist_id in similar[0:i].artist_id.values:
similar.drop(similar.index[i], inplace=True)
else:
i += 1
# Return the top nine most similar albums
similar = similar[0:9]
cache.set("similar", similar)
return similar
def get_artist_df():
artist_df = cache.get("artist_df")
if artist_df is None:
artist_df = pd.read_csv(path.join('.', 'data', 'artists.csv'),
header=0,
low_memory=False,
converters={
'member_list':
lambda x: x[1:-1].split(', '),
'group_list': lambda x: x[1:-1].split(', ')
})
cache.set("artist_df", artist_df)
return artist_df
def get_dict():
return cache.get("release_dict")
def search(string):
df = cache.get("df")
matches = df['artist_name'].str.contains(
string, case=False) | df['release_name'].str.contains(string,
case=False)
return df[matches]
def get_top_ten():
return cache.get("top_ten")
def get_df():
df = cache.get("df")
if df is None:
transform_data(get_dict())
df = cache.get("df")
return df