Spaces:
Sleeping
Sleeping
Update app.py
Browse files
app.py
CHANGED
|
@@ -9,11 +9,13 @@ from collections import Counter
|
|
| 9 |
import numpy as np
|
| 10 |
|
| 11 |
# Function to load data from SQLite database
|
|
|
|
| 12 |
def load_data(db_file):
|
| 13 |
conn = sqlite3.connect(db_file)
|
| 14 |
return conn
|
| 15 |
|
| 16 |
# Function to fetch genre movie releases by year
|
|
|
|
| 17 |
def fetch_genre_movie_releases(conn):
|
| 18 |
query = r'''
|
| 19 |
SELECT startYear, genres
|
|
@@ -35,6 +37,7 @@ def fetch_genre_movie_releases(conn):
|
|
| 35 |
return genre_counts
|
| 36 |
|
| 37 |
# Function to fetch data for filled line chart of movie release years
|
|
|
|
| 38 |
def fetch_movie_release_years(conn):
|
| 39 |
query_release_years = r'''
|
| 40 |
SELECT startYear, COUNT(*) as count
|
|
@@ -47,6 +50,7 @@ def fetch_movie_release_years(conn):
|
|
| 47 |
return df_release_years
|
| 48 |
|
| 49 |
# Function to fetch data and create box plot of average rating by first_genre
|
|
|
|
| 50 |
def fetch_and_plot_average_rating_by_genre(conn):
|
| 51 |
query = r'''
|
| 52 |
SELECT tb.tconst, tb.primaryTitle, tr.averageRating, tb.genres
|
|
@@ -57,7 +61,7 @@ def fetch_and_plot_average_rating_by_genre(conn):
|
|
| 57 |
df = pd.read_sql_query(query, conn)
|
| 58 |
|
| 59 |
# Function to extract the first genre from the genres list
|
| 60 |
-
|
| 61 |
if genres:
|
| 62 |
return genres.split(',')[0].strip()
|
| 63 |
else:
|
|
@@ -103,6 +107,7 @@ def create_genre_wordcloud(conn):
|
|
| 103 |
st.pyplot(plt.gcf()) # Pass the current figure explicitly to st.pyplot()
|
| 104 |
|
| 105 |
# Function to find best movie of each genre by numVotes * averageRating
|
|
|
|
| 106 |
def find_best_movies_by_genre(conn):
|
| 107 |
query = r'''
|
| 108 |
SELECT tb.tconst, tb.primaryTitle, tb.startYear, tb.genres, tr.averageRating, tr.numVotes
|
|
@@ -126,6 +131,7 @@ def find_best_movies_by_genre(conn):
|
|
| 126 |
return best_movies_by_genre
|
| 127 |
|
| 128 |
# Function to plot stacked area chart of genre movie releases by year using Plotly Express
|
|
|
|
| 129 |
def plot_stacked_genre_movie_releases(genre_counts):
|
| 130 |
fig = px.area(genre_counts, x='startYear', y='count', color='genres',
|
| 131 |
title='Stacked Genre Movie Releases by Year',
|
|
@@ -146,6 +152,7 @@ def plot_stacked_genre_movie_releases(genre_counts):
|
|
| 146 |
return fig
|
| 147 |
|
| 148 |
# Function to plot global map of total films per region using Plotly Express
|
|
|
|
| 149 |
def plot_global_map():
|
| 150 |
df = pd.read_csv('movie_region.csv')
|
| 151 |
# Country code to name mapping
|
|
@@ -241,6 +248,7 @@ def plot_global_map():
|
|
| 241 |
|
| 242 |
|
| 243 |
# Function to fetch summary info
|
|
|
|
| 244 |
def fetch_summary_info(conn):
|
| 245 |
# Fetch total count of movies
|
| 246 |
query_total_movies = r'''
|
|
|
|
| 9 |
import numpy as np
|
| 10 |
|
| 11 |
# Function to load data from SQLite database
|
| 12 |
+
@st.cache_data
|
| 13 |
def load_data(db_file):
|
| 14 |
conn = sqlite3.connect(db_file)
|
| 15 |
return conn
|
| 16 |
|
| 17 |
# Function to fetch genre movie releases by year
|
| 18 |
+
@st.cache_data
|
| 19 |
def fetch_genre_movie_releases(conn):
|
| 20 |
query = r'''
|
| 21 |
SELECT startYear, genres
|
|
|
|
| 37 |
return genre_counts
|
| 38 |
|
| 39 |
# Function to fetch data for filled line chart of movie release years
|
| 40 |
+
@st.cache_data
|
| 41 |
def fetch_movie_release_years(conn):
|
| 42 |
query_release_years = r'''
|
| 43 |
SELECT startYear, COUNT(*) as count
|
|
|
|
| 50 |
return df_release_years
|
| 51 |
|
| 52 |
# Function to fetch data and create box plot of average rating by first_genre
|
| 53 |
+
@st.cache_data
|
| 54 |
def fetch_and_plot_average_rating_by_genre(conn):
|
| 55 |
query = r'''
|
| 56 |
SELECT tb.tconst, tb.primaryTitle, tr.averageRating, tb.genres
|
|
|
|
| 61 |
df = pd.read_sql_query(query, conn)
|
| 62 |
|
| 63 |
# Function to extract the first genre from the genres list
|
| 64 |
+
def extract_first_genre(genres):
|
| 65 |
if genres:
|
| 66 |
return genres.split(',')[0].strip()
|
| 67 |
else:
|
|
|
|
| 107 |
st.pyplot(plt.gcf()) # Pass the current figure explicitly to st.pyplot()
|
| 108 |
|
| 109 |
# Function to find best movie of each genre by numVotes * averageRating
|
| 110 |
+
@st.cache_data
|
| 111 |
def find_best_movies_by_genre(conn):
|
| 112 |
query = r'''
|
| 113 |
SELECT tb.tconst, tb.primaryTitle, tb.startYear, tb.genres, tr.averageRating, tr.numVotes
|
|
|
|
| 131 |
return best_movies_by_genre
|
| 132 |
|
| 133 |
# Function to plot stacked area chart of genre movie releases by year using Plotly Express
|
| 134 |
+
@st.cache_data
|
| 135 |
def plot_stacked_genre_movie_releases(genre_counts):
|
| 136 |
fig = px.area(genre_counts, x='startYear', y='count', color='genres',
|
| 137 |
title='Stacked Genre Movie Releases by Year',
|
|
|
|
| 152 |
return fig
|
| 153 |
|
| 154 |
# Function to plot global map of total films per region using Plotly Express
|
| 155 |
+
@st.cache_data
|
| 156 |
def plot_global_map():
|
| 157 |
df = pd.read_csv('movie_region.csv')
|
| 158 |
# Country code to name mapping
|
|
|
|
| 248 |
|
| 249 |
|
| 250 |
# Function to fetch summary info
|
| 251 |
+
@st.cache_data
|
| 252 |
def fetch_summary_info(conn):
|
| 253 |
# Fetch total count of movies
|
| 254 |
query_total_movies = r'''
|