Spaces:
Runtime error
Runtime error
Create app.py
Browse files
app.py
ADDED
|
@@ -0,0 +1,732 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
import pandas as pd
|
| 2 |
+
import numpy as np
|
| 3 |
+
import matplotlib.pyplot as plt
|
| 4 |
+
import seaborn as sns
|
| 5 |
+
from datetime import datetime, timedelta
|
| 6 |
+
from sklearn.linear_model import LinearRegression
|
| 7 |
+
import warnings
|
| 8 |
+
import re
|
| 9 |
+
import io
|
| 10 |
+
import time
|
| 11 |
+
from difflib import SequenceMatcher
|
| 12 |
+
import gradio as gr
|
| 13 |
+
import google.generativeai as genai
|
| 14 |
+
from typing import List, Dict, Tuple, Optional
|
| 15 |
+
import tempfile
|
| 16 |
+
import os
|
| 17 |
+
|
| 18 |
+
# Suppress warnings for a cleaner output
|
| 19 |
+
warnings.filterwarnings('ignore')
|
| 20 |
+
|
| 21 |
+
def get_now():
|
| 22 |
+
"""A simple function to get the current time. Can be mocked for testing."""
|
| 23 |
+
return datetime.now()
|
| 24 |
+
|
| 25 |
+
class ComprehensivePodcastReport:
|
| 26 |
+
"""
|
| 27 |
+
Generates a complete podcast performance report, combining overall analytics
|
| 28 |
+
with detailed daily and cumulative analysis of episodes within a specified period.
|
| 29 |
+
"""
|
| 30 |
+
|
| 31 |
+
def __init__(self, client_name):
|
| 32 |
+
"""Initialize the report generator."""
|
| 33 |
+
self.client_name = client_name
|
| 34 |
+
self.all_time_data = {}
|
| 35 |
+
self.period_data = {}
|
| 36 |
+
self.episode_specific_data = {}
|
| 37 |
+
self.unmatched_episode_csvs = []
|
| 38 |
+
self.title_translation_cache = {}
|
| 39 |
+
self.report_date = get_now().strftime("%B %d, %Y")
|
| 40 |
+
self.date_range_str = "All Time"
|
| 41 |
+
self.start_date = None
|
| 42 |
+
self.end_date = None
|
| 43 |
+
self.gemini_api_key = None
|
| 44 |
+
|
| 45 |
+
# --- DATA LOADING AND PREPARATION METHODS ---
|
| 46 |
+
|
| 47 |
+
def _fix_spotify_timestamps(self, timestamp_series):
|
| 48 |
+
"""Fix Spotify's invalid '24:00:00' timestamps."""
|
| 49 |
+
return timestamp_series.astype(str).str.replace('24:00:00', '23:59:59')
|
| 50 |
+
|
| 51 |
+
def load_general_data(self, file_paths):
|
| 52 |
+
"""Load all general CSV files (OnSpotify, EpisodeRankings, etc.)."""
|
| 53 |
+
print("📊 Loading and processing general data files...")
|
| 54 |
+
try:
|
| 55 |
+
self.all_time_data['time_series'] = pd.read_csv(file_paths['time_series'])
|
| 56 |
+
self.all_time_data['time_series']['Date'] = pd.to_datetime(self._fix_spotify_timestamps(self.all_time_data['time_series']['Time (UTC)']))
|
| 57 |
+
|
| 58 |
+
self.all_time_data['episodes'] = pd.read_csv(file_paths['episodes'])
|
| 59 |
+
self.all_time_data['episodes']['Publish Date'] = pd.to_datetime(self._fix_spotify_timestamps(self.all_time_data['episodes']['Publish Time (UTC)'])).dt.normalize()
|
| 60 |
+
except KeyError as e:
|
| 61 |
+
print(f"❌ Missing a required file: {e}. Please include OnSpotify and EpisodeRankings files.")
|
| 62 |
+
raise
|
| 63 |
+
|
| 64 |
+
# Optional Files
|
| 65 |
+
if 'streams' in file_paths:
|
| 66 |
+
self.all_time_data['streams'] = pd.read_csv(file_paths['streams'])
|
| 67 |
+
self.all_time_data['streams']['Date'] = pd.to_datetime(self._fix_spotify_timestamps(self.all_time_data['streams']['Time (UTC)']))
|
| 68 |
+
streams_df = self.all_time_data['streams']
|
| 69 |
+
first_nonzero_idx = streams_df[streams_df['Streams & Downloads'] > 0].index.min()
|
| 70 |
+
if pd.notna(first_nonzero_idx):
|
| 71 |
+
self.all_time_data['streams'] = streams_df.loc[first_nonzero_idx:].reset_index(drop=True)
|
| 72 |
+
|
| 73 |
+
if 'geo' in file_paths: self.all_time_data['geo'] = pd.read_csv(file_paths['geo'])
|
| 74 |
+
if 'apps' in file_paths: self.all_time_data['apps'] = pd.read_csv(file_paths['apps'])
|
| 75 |
+
if 'devices' in file_paths: self.all_time_data['devices'] = pd.read_csv(file_paths['devices'])
|
| 76 |
+
|
| 77 |
+
self.period_data = {key: df.copy() for key, df in self.all_time_data.items()}
|
| 78 |
+
print(f"✅ General data loaded successfully for {self.client_name}")
|
| 79 |
+
|
| 80 |
+
def filter_data_by_date(self, start_date, end_date):
|
| 81 |
+
"""Filter the loaded data to a specific date range."""
|
| 82 |
+
self.start_date = pd.to_datetime(start_date).normalize()
|
| 83 |
+
self.end_date = pd.to_datetime(end_date).normalize()
|
| 84 |
+
self.date_range_str = f"{self.start_date.strftime('%Y-%m-%d')} to {self.end_date.strftime('%Y-%m-%d')}"
|
| 85 |
+
print(f"🔎 Filtering data for period: {self.date_range_str}")
|
| 86 |
+
|
| 87 |
+
for key in ['time_series', 'streams']:
|
| 88 |
+
if key in self.period_data:
|
| 89 |
+
df = self.period_data[key]
|
| 90 |
+
self.period_data[key] = df[(df['Date'] >= self.start_date) & (df['Date'] <= self.end_date)]
|
| 91 |
+
|
| 92 |
+
# --- EPISODE-SPECIFIC ANALYSIS METHODS ---
|
| 93 |
+
|
| 94 |
+
def _normalize_text(self, text):
|
| 95 |
+
"""Normalizes text for fuzzy string matching."""
|
| 96 |
+
text = re.sub(r'[^\u0590-\u05FFa-zA-Z0-9\-]', '', str(text).replace(':', '').replace(' ', ''))
|
| 97 |
+
return text.lower()
|
| 98 |
+
|
| 99 |
+
def identify_and_prompt_for_episodes(self):
|
| 100 |
+
"""Identifies episodes in the period and prompts the user for their CSVs."""
|
| 101 |
+
episodes_df = self.all_time_data.get('episodes')
|
| 102 |
+
if episodes_df is None: return pd.DataFrame()
|
| 103 |
+
|
| 104 |
+
episodes_in_period = episodes_df[
|
| 105 |
+
(episodes_df['Publish Date'] >= self.start_date) &
|
| 106 |
+
(episodes_df['Publish Date'] <= self.end_date)
|
| 107 |
+
].sort_values('Publish Date', ascending=False).reset_index(drop=True)
|
| 108 |
+
|
| 109 |
+
total_episodes = len(episodes_in_period)
|
| 110 |
+
if total_episodes == 0:
|
| 111 |
+
print("\n⚠️ No episodes found published in the selected period.")
|
| 112 |
+
else:
|
| 113 |
+
print(f"\n📺 Found {total_episodes} episodes published in the period:")
|
| 114 |
+
print("="*80)
|
| 115 |
+
for _, row in episodes_in_period.iterrows():
|
| 116 |
+
print(f" • {row['Episode Title'][:80]} (Published: {row['Publish Date']:%Y-%m-%d})")
|
| 117 |
+
print("="*80)
|
| 118 |
+
return episodes_in_period
|
| 119 |
+
|
| 120 |
+
def load_and_match_episode_csvs(self, uploaded_files, episodes_in_period):
|
| 121 |
+
"""Matches and loads individual episode CSVs from uploaded files."""
|
| 122 |
+
print("\n🔍 Matching and loading individual episode CSVs...")
|
| 123 |
+
if episodes_in_period.empty:
|
| 124 |
+
print(" -> No episodes in period to match against. Skipping.")
|
| 125 |
+
return
|
| 126 |
+
episodes_in_period['normalized_title'] = episodes_in_period['Episode Title'].apply(self._normalize_text)
|
| 127 |
+
|
| 128 |
+
for filename, file_content in uploaded_files.items():
|
| 129 |
+
file_type = 'spotify' if 'OnSpotify' in filename else 'all_platforms' if 'StreamsAndDownloads' in filename else None
|
| 130 |
+
if not file_type: continue
|
| 131 |
+
|
| 132 |
+
clean_filename = re.sub(r'\s*\(\d+\)|\s+\d+(?=\.csv)', '', filename)
|
| 133 |
+
normalized_filename = self._normalize_text(clean_filename)
|
| 134 |
+
episodes_in_period['similarity'] = episodes_in_period['normalized_title'].apply(
|
| 135 |
+
lambda title: SequenceMatcher(None, normalized_filename, title).ratio()
|
| 136 |
+
)
|
| 137 |
+
best_match = episodes_in_period.loc[episodes_in_period['similarity'].idxmax()]
|
| 138 |
+
|
| 139 |
+
if best_match['similarity'] > 0.5:
|
| 140 |
+
episode_title = best_match['Episode Title']
|
| 141 |
+
print(f" ✅ Matched: {filename[:40]}... -> {episode_title[:40]}...")
|
| 142 |
+
try:
|
| 143 |
+
df = pd.read_csv(io.StringIO(file_content))
|
| 144 |
+
df['Date'] = pd.to_datetime(df['Time (UTC)'].str.split(',').str[0], errors='coerce').dt.normalize()
|
| 145 |
+
value_col = next((col for col in ['Plays', 'Streams & Downloads'] if col in df.columns), None)
|
| 146 |
+
if not value_col: continue
|
| 147 |
+
episode_df = df[['Date', value_col]].rename(columns={value_col: 'value'}).groupby('Date')['value'].sum().reset_index()
|
| 148 |
+
if episode_title not in self.episode_specific_data: self.episode_specific_data[episode_title] = {}
|
| 149 |
+
self.episode_specific_data[episode_title][file_type] = episode_df
|
| 150 |
+
except Exception as e:
|
| 151 |
+
print(f" -> Error processing file {filename}: {e}")
|
| 152 |
+
else:
|
| 153 |
+
self.unmatched_episode_csvs.append(filename)
|
| 154 |
+
|
| 155 |
+
# --- CORE ANALYTICS AND METRICS ---
|
| 156 |
+
|
| 157 |
+
def calculate_key_metrics(self, use_all_time=False):
|
| 158 |
+
"""Calculate core performance metrics."""
|
| 159 |
+
data_scope = self.all_time_data if use_all_time else self.period_data
|
| 160 |
+
ts_data = data_scope.get('time_series', pd.DataFrame())
|
| 161 |
+
if ts_data.empty: return {}
|
| 162 |
+
ts_followers_cleaned = ts_data.dropna(subset=['Followers'])
|
| 163 |
+
current_followers = int(ts_followers_cleaned['Followers'].iloc[-1]) if not ts_followers_cleaned.empty else 0
|
| 164 |
+
total_plays = ts_data['Plays'].sum()
|
| 165 |
+
total_streams = ts_data['Streams'].sum()
|
| 166 |
+
|
| 167 |
+
metrics = {
|
| 168 |
+
'total_plays': int(total_plays), 'total_streams': int(total_streams),
|
| 169 |
+
'avg_daily_plays': ts_data['Plays'].mean(),
|
| 170 |
+
'engagement_percentage': (total_streams / max(total_plays, 1)) * 100,
|
| 171 |
+
'current_followers': current_followers
|
| 172 |
+
}
|
| 173 |
+
if use_all_time:
|
| 174 |
+
ep_data = self.all_time_data.get('episodes', pd.DataFrame())
|
| 175 |
+
metrics.update({
|
| 176 |
+
'total_episodes': len(ep_data),
|
| 177 |
+
'median_streams_per_episode': ep_data['Streams & Downloads'].median() if not ep_data.empty else 0,
|
| 178 |
+
'performance_benchmark': ep_data['Streams & Downloads'].quantile(0.75) if not ep_data.empty else 0
|
| 179 |
+
})
|
| 180 |
+
else: # Period specific
|
| 181 |
+
ep_data_all = self.all_time_data.get('episodes', pd.DataFrame())
|
| 182 |
+
episodes_in_period = ep_data_all[(ep_data_all['Publish Date'] >= self.start_date) & (ep_data_all['Publish Date'] <= self.end_date)]
|
| 183 |
+
metrics['performance_benchmark_period'] = episodes_in_period['Streams & Downloads'].quantile(0.75) if not episodes_in_period.empty else 0
|
| 184 |
+
return metrics
|
| 185 |
+
|
| 186 |
+
def analyze_growth_trends(self, period_days=30):
|
| 187 |
+
"""Analyze growth trends for the selected period."""
|
| 188 |
+
ts_data = self.period_data['time_series'].dropna(subset=['Plays', 'Followers']).sort_values('Date')
|
| 189 |
+
if len(ts_data) < period_days * 2: return {}
|
| 190 |
+
recent_period = ts_data.tail(period_days)
|
| 191 |
+
previous_period = ts_data.iloc[-(period_days*2):-period_days]
|
| 192 |
+
if recent_period.empty or previous_period.empty: return {}
|
| 193 |
+
recent_gain = recent_period['Followers'].iloc[-1] - recent_period['Followers'].iloc[0]
|
| 194 |
+
previous_gain = previous_period['Followers'].iloc[-1] - previous_period['Followers'].iloc[0]
|
| 195 |
+
return {
|
| 196 |
+
'plays_growth_rate_median': ((recent_period['Plays'].median() - previous_period['Plays'].median()) / max(previous_period['Plays'].median(), 1)) * 100,
|
| 197 |
+
'followers_gained': int(recent_gain),
|
| 198 |
+
'follower_growth_rate': ((recent_gain - previous_gain) / max(abs(previous_gain), 1)) * 100 if previous_gain != 0 else float('inf')
|
| 199 |
+
}
|
| 200 |
+
|
| 201 |
+
def analyze_seasonal_patterns(self):
|
| 202 |
+
"""Analyze weekly listening patterns."""
|
| 203 |
+
ts_data = self.period_data['time_series'].dropna(subset=['Plays'])
|
| 204 |
+
if len(ts_data) < 7: return {}
|
| 205 |
+
ts_data['DayOfWeek'] = ts_data['Date'].dt.day_name()
|
| 206 |
+
weekly_avg = ts_data.groupby('DayOfWeek')['Plays'].mean()
|
| 207 |
+
return {
|
| 208 |
+
'best_day': weekly_avg.idxmax(), 'worst_day': weekly_avg.idxmin(),
|
| 209 |
+
'weekly_consistency': (1 - (weekly_avg.std() / weekly_avg.mean())) * 100 if weekly_avg.mean() > 0 else 0
|
| 210 |
+
}
|
| 211 |
+
|
| 212 |
+
def _get_platform_share(self, platform_name):
|
| 213 |
+
"""Helper to get platform share from all-time data."""
|
| 214 |
+
apps_df = self.all_time_data.get('apps')
|
| 215 |
+
if apps_df is None: return 0.0
|
| 216 |
+
platform_row = apps_df[apps_df['App'] == platform_name]
|
| 217 |
+
return platform_row['Percent of Plays'].iloc[0] * 100 if not platform_row.empty else 0.0
|
| 218 |
+
|
| 219 |
+
# --- PLOTTING AND VISUALIZATION METHODS ---
|
| 220 |
+
|
| 221 |
+
def _add_regression_line(self, ax, x_values, y_values, **kwargs):
|
| 222 |
+
"""Helper to add a linear regression trendline to a plot."""
|
| 223 |
+
if len(x_values) < 2: return
|
| 224 |
+
x_numeric = np.arange(len(x_values))
|
| 225 |
+
model = LinearRegression().fit(x_numeric.reshape(-1, 1), y_values)
|
| 226 |
+
y_pred = model.predict(x_numeric.reshape(-1, 1))
|
| 227 |
+
label = f"{kwargs.get('label_prefix', 'Trend')} (Slope: {model.coef_[0]:.2f})"
|
| 228 |
+
ax.plot(x_values, y_pred, '--', color='red', alpha=0.7, label=label)
|
| 229 |
+
|
| 230 |
+
def generate_all_visualizations(self):
|
| 231 |
+
"""Generates a comprehensive set of all overview plots."""
|
| 232 |
+
print("🎨 Generating all performance visualizations...")
|
| 233 |
+
plots = []
|
| 234 |
+
ts_data = self.period_data['time_series'].sort_values('Date')
|
| 235 |
+
|
| 236 |
+
# Daily Plays & Streams
|
| 237 |
+
if not ts_data.empty:
|
| 238 |
+
fig, ax = plt.subplots(figsize=(12, 6))
|
| 239 |
+
ax.plot(ts_data['Date'], ts_data['Plays'], label='Daily Plays (Spotify)', color='blue')
|
| 240 |
+
self._add_regression_line(ax, ts_data['Date'], ts_data['Plays'])
|
| 241 |
+
ax.set_title(f'{self.client_name} - Daily Plays (OnSpotify)', fontsize=14)
|
| 242 |
+
ax.grid(True, alpha=0.3)
|
| 243 |
+
ax.legend()
|
| 244 |
+
plt.tight_layout()
|
| 245 |
+
plots.append(('daily_plays', fig))
|
| 246 |
+
|
| 247 |
+
if 'streams' in self.period_data and not self.period_data['streams'].empty:
|
| 248 |
+
streams_data = self.period_data['streams'].sort_values('Date')
|
| 249 |
+
fig, ax = plt.subplots(figsize=(12, 6))
|
| 250 |
+
ax.plot(streams_data['Date'], streams_data['Streams & Downloads'], label='Daily Streams & Downloads', color='green')
|
| 251 |
+
self._add_regression_line(ax, streams_data['Date'], streams_data['Streams & Downloads'])
|
| 252 |
+
ax.set_title(f'{self.client_name} - Daily Streams & Downloads (All Platforms)', fontsize=14)
|
| 253 |
+
ax.grid(True, alpha=0.3)
|
| 254 |
+
ax.legend()
|
| 255 |
+
plt.tight_layout()
|
| 256 |
+
plots.append(('daily_streams', fig))
|
| 257 |
+
|
| 258 |
+
# Monthly Plots
|
| 259 |
+
graph_start = self.start_date.replace(day=1) if self.start_date.day != 1 else self.start_date
|
| 260 |
+
for key, col, color in [('time_series', 'Plays', 'skyblue'), ('streams', 'Streams & Downloads', 'lightgreen')]:
|
| 261 |
+
if key in self.all_time_data:
|
| 262 |
+
monthly_data = self.all_time_data[key]
|
| 263 |
+
monthly_data = monthly_data[(monthly_data['Date'] >= graph_start) & (monthly_data['Date'] <= self.end_date)]
|
| 264 |
+
if not monthly_data.empty:
|
| 265 |
+
monthly_data['YearMonth'] = monthly_data['Date'].dt.to_period('M')
|
| 266 |
+
monthly_values = monthly_data.groupby('YearMonth')[col].sum()
|
| 267 |
+
fig, ax = plt.subplots(figsize=(12, 6))
|
| 268 |
+
bars = ax.bar(np.arange(len(monthly_values)), monthly_values.values, color=color, edgecolor='navy')
|
| 269 |
+
self._add_regression_line(ax, np.arange(len(monthly_values)), monthly_values.values)
|
| 270 |
+
ax.set_xticks(np.arange(len(monthly_values)))
|
| 271 |
+
ax.set_xticklabels([str(p) for p in monthly_values.index], rotation=45)
|
| 272 |
+
ax.set_title(f'{self.client_name} - Monthly {col}', fontsize=14)
|
| 273 |
+
ax.legend()
|
| 274 |
+
plt.tight_layout()
|
| 275 |
+
current_month = pd.Period(get_now(), 'M')
|
| 276 |
+
if current_month in monthly_values.index:
|
| 277 |
+
bars[monthly_values.index.get_loc(current_month)].set_color('orange')
|
| 278 |
+
plots.append((f'monthly_{key}', fig))
|
| 279 |
+
|
| 280 |
+
# Advanced Metrics
|
| 281 |
+
follower_data = ts_data.dropna(subset=['Followers'])
|
| 282 |
+
if not follower_data.empty:
|
| 283 |
+
fig, ax = plt.subplots(figsize=(12, 6))
|
| 284 |
+
ax.plot(follower_data['Date'], follower_data['Followers'], label='Followers', color='purple')
|
| 285 |
+
self._add_regression_line(ax, follower_data['Date'], follower_data['Followers'], label_prefix="Follower Trend")
|
| 286 |
+
ax.set_title(f'{self.client_name} - Follower Growth', fontsize=14)
|
| 287 |
+
ax.grid(True, alpha=0.3)
|
| 288 |
+
ax.legend()
|
| 289 |
+
plt.tight_layout()
|
| 290 |
+
plots.append(('follower_growth', fig))
|
| 291 |
+
|
| 292 |
+
consump_data = ts_data.dropna(subset=['Consumption Hours'])
|
| 293 |
+
if not consump_data.empty and consump_data['Consumption Hours'].sum() > 0:
|
| 294 |
+
fig, ax = plt.subplots(figsize=(12, 6))
|
| 295 |
+
ax.plot(consump_data['Date'], consump_data['Consumption Hours'], label='Hours', color='teal')
|
| 296 |
+
self._add_regression_line(ax, consump_data['Date'], consump_data['Consumption Hours'], label_prefix="Consumption Trend")
|
| 297 |
+
ax.set_title(f'{self.client_name} - Daily Consumption Hours', fontsize=14)
|
| 298 |
+
ax.grid(True, alpha=0.3)
|
| 299 |
+
ax.legend()
|
| 300 |
+
plt.tight_layout()
|
| 301 |
+
plots.append(('consumption_hours', fig))
|
| 302 |
+
|
| 303 |
+
ratio_df = ts_data[['Date', 'Streams', 'Plays']].copy()
|
| 304 |
+
ratio_df['ratio'] = ratio_df['Streams'] / ratio_df['Plays'].replace(0, np.nan)
|
| 305 |
+
ratio_df['ratio_30d_avg'] = ratio_df['ratio'].rolling(30, min_periods=1).mean()
|
| 306 |
+
ratio_df.dropna(subset=['ratio_30d_avg'], inplace=True)
|
| 307 |
+
if not ratio_df.empty:
|
| 308 |
+
fig, ax = plt.subplots(figsize=(12, 6))
|
| 309 |
+
ax.plot(ratio_df['Date'], ratio_df['ratio_30d_avg'], label='30-Day Avg Stream/Play Ratio', color='orange')
|
| 310 |
+
self._add_regression_line(ax, ratio_df['Date'], ratio_df['ratio_30d_avg'], label_prefix="Ratio Trend")
|
| 311 |
+
ax.set_title(f'{self.client_name} - Stream/Play Ratio (30-Day Average)', fontsize=14)
|
| 312 |
+
ax.grid(True, alpha=0.3)
|
| 313 |
+
ax.legend()
|
| 314 |
+
plt.tight_layout()
|
| 315 |
+
plots.append(('stream_play_ratio', fig))
|
| 316 |
+
|
| 317 |
+
# Audience & Episode Distributions (All-Time)
|
| 318 |
+
if 'apps' in self.all_time_data:
|
| 319 |
+
fig, ax = plt.subplots(figsize=(8, 8))
|
| 320 |
+
self.all_time_data['apps'].head(5).plot.pie(y='Percent of Plays', labels=self.all_time_data['apps']['App'].head(5), autopct='%1.1f%%', ax=ax, legend=False)
|
| 321 |
+
ax.set_title(f'{self.client_name} - Platform Distribution', fontsize=14)
|
| 322 |
+
ax.set_ylabel('')
|
| 323 |
+
plt.tight_layout()
|
| 324 |
+
plots.append(('platform_dist', fig))
|
| 325 |
+
|
| 326 |
+
if 'devices' in self.all_time_data:
|
| 327 |
+
fig, ax = plt.subplots(figsize=(8, 8))
|
| 328 |
+
self.all_time_data['devices'].head(5).plot.pie(y='Percent of Plays', labels=self.all_time_data['devices']['Device'].head(5), autopct='%1.1f%%', ax=ax, legend=False)
|
| 329 |
+
ax.set_title(f'{self.client_name} - Device Distribution', fontsize=14)
|
| 330 |
+
ax.set_ylabel('')
|
| 331 |
+
plt.tight_layout()
|
| 332 |
+
plots.append(('device_dist', fig))
|
| 333 |
+
|
| 334 |
+
if 'geo' in self.all_time_data:
|
| 335 |
+
fig, ax = plt.subplots(figsize=(10, 6))
|
| 336 |
+
top_geo = self.all_time_data['geo'].head(10)
|
| 337 |
+
ax.barh(top_geo['Geo'], top_geo['Percent of Plays'] * 100, color='coral')
|
| 338 |
+
ax.set_title(f'{self.client_name} - Top 10 Geographic Markets', fontsize=14)
|
| 339 |
+
ax.invert_yaxis()
|
| 340 |
+
ax.grid(True, alpha=0.3, axis='x')
|
| 341 |
+
plt.tight_layout()
|
| 342 |
+
plots.append(('geo_markets', fig))
|
| 343 |
+
|
| 344 |
+
ep_data_all = self.all_time_data.get('episodes')
|
| 345 |
+
if ep_data_all is not None:
|
| 346 |
+
fig, ax = plt.subplots(figsize=(10, 6))
|
| 347 |
+
ax.hist(ep_data_all['Streams & Downloads'], bins=30, color='skyblue', edgecolor='navy')
|
| 348 |
+
ax.axvline(ep_data_all['Streams & Downloads'].mean(), color='red', linestyle='--', label='Mean')
|
| 349 |
+
ax.set_title(f'{self.client_name} - Episode Performance Distribution (All Time)', fontsize=14)
|
| 350 |
+
ax.legend()
|
| 351 |
+
plt.tight_layout()
|
| 352 |
+
plots.append(('ep_dist_all_time', fig))
|
| 353 |
+
|
| 354 |
+
episodes_in_period = ep_data_all[(ep_data_all['Publish Date'] >= self.start_date) & (ep_data_all['Publish Date'] <= self.end_date)]
|
| 355 |
+
if not episodes_in_period.empty:
|
| 356 |
+
fig, ax = plt.subplots(figsize=(10, 6))
|
| 357 |
+
ax.hist(episodes_in_period['Streams & Downloads'], bins=15, color='teal', edgecolor='darkslategray')
|
| 358 |
+
ax.axvline(episodes_in_period['Streams & Downloads'].mean(), color='red', linestyle='--', label='Mean')
|
| 359 |
+
ax.set_title(f'{self.client_name} - Episode Performance (Published in Period)', fontsize=14)
|
| 360 |
+
ax.legend()
|
| 361 |
+
plt.tight_layout()
|
| 362 |
+
plots.append(('ep_dist_period', fig))
|
| 363 |
+
|
| 364 |
+
return plots
|
| 365 |
+
|
| 366 |
+
def _translate_title(self, hebrew_title):
|
| 367 |
+
"""Translates a Hebrew title to a short English legend title using Gemini."""
|
| 368 |
+
if hebrew_title in self.title_translation_cache:
|
| 369 |
+
return self.title_translation_cache[hebrew_title]
|
| 370 |
+
|
| 371 |
+
if not self.gemini_api_key:
|
| 372 |
+
return hebrew_title[:40] + '...'
|
| 373 |
+
|
| 374 |
+
try:
|
| 375 |
+
genai.configure(api_key=self.gemini_api_key)
|
| 376 |
+
model = genai.GenerativeModel('gemini-2.0-flash-exp')
|
| 377 |
+
prompt = f"""Analyze the Hebrew podcast title "{hebrew_title}". Generate a short, readable English legend title formatted as "[Guest Name] - #[Episode Number]". Transliterate the name. If there is no episode number, use only the name. If there is no name, create a concise English summary of the topic. If you recognize מהדורת מוסף in the title, then the output would be: "Investors Panel - #[Episode Number]".The final title must be under 5 words."""
|
| 378 |
+
response = model.generate_content(prompt)
|
| 379 |
+
time.sleep(1.5)
|
| 380 |
+
translated = response.text.strip()
|
| 381 |
+
self.title_translation_cache[hebrew_title] = translated
|
| 382 |
+
return translated
|
| 383 |
+
except Exception as e:
|
| 384 |
+
print(f" -> Gemini API Error: {e}")
|
| 385 |
+
return hebrew_title[:40] + '...'
|
| 386 |
+
|
| 387 |
+
def generate_episode_specific_plots(self, max_episodes=10):
|
| 388 |
+
"""Generates the cumulative performance plots for individual episodes."""
|
| 389 |
+
print("🚀 Generating episode-specific cumulative plots...")
|
| 390 |
+
plots = []
|
| 391 |
+
if not self.episode_specific_data: return plots
|
| 392 |
+
|
| 393 |
+
for data_source in ['spotify', 'all_platforms']:
|
| 394 |
+
ep_data_source = {t: d[data_source] for t, d in self.episode_specific_data.items() if data_source in d}
|
| 395 |
+
if not ep_data_source: continue
|
| 396 |
+
|
| 397 |
+
ep_totals = {title: df['value'].sum() for title, df in ep_data_source.items()}
|
| 398 |
+
top_episodes = sorted(ep_totals, key=ep_totals.get, reverse=True)[:max_episodes]
|
| 399 |
+
|
| 400 |
+
date_index = pd.date_range(start=self.start_date, end=self.end_date, freq='D')
|
| 401 |
+
plot_df = pd.DataFrame(index=date_index)
|
| 402 |
+
|
| 403 |
+
for title in top_episodes:
|
| 404 |
+
plot_df = plot_df.join(ep_data_source[title].set_index('Date').rename(columns={'value': title}))
|
| 405 |
+
|
| 406 |
+
cumulative_df = plot_df.fillna(0).cumsum()
|
| 407 |
+
fig, ax = plt.subplots(figsize=(15, 8))
|
| 408 |
+
|
| 409 |
+
for h_title in cumulative_df.columns:
|
| 410 |
+
ax.plot(cumulative_df.index, cumulative_df[h_title], label=self._translate_title(h_title), linewidth=2.5)
|
| 411 |
+
|
| 412 |
+
ax.set_title(f'Cumulative Performance by Date ({data_source.replace("_", " ").title()})', fontsize=16)
|
| 413 |
+
ax.legend(bbox_to_anchor=(1.02, 1), loc='upper left')
|
| 414 |
+
plt.tight_layout()
|
| 415 |
+
plots.append((f'ep_cumul_date_{data_source}', fig))
|
| 416 |
+
|
| 417 |
+
airday_df = pd.DataFrame()
|
| 418 |
+
for title in top_episodes:
|
| 419 |
+
df = ep_data_source[title]
|
| 420 |
+
first_play = df[df['value'] > 0]['Date'].min()
|
| 421 |
+
if pd.isna(first_play): continue
|
| 422 |
+
df_after = df[df['Date'] >= first_play].copy()
|
| 423 |
+
airday_df[title] = df_after['value'].cumsum().reset_index(drop=True)
|
| 424 |
+
|
| 425 |
+
airday_df['Average'] = airday_df.mean(axis=1)
|
| 426 |
+
fig, ax = plt.subplots(figsize=(15, 8))
|
| 427 |
+
|
| 428 |
+
for h_title in top_episodes:
|
| 429 |
+
if h_title in airday_df.columns:
|
| 430 |
+
ax.plot(airday_df.index + 1, airday_df[h_title], label=self._translate_title(h_title), alpha=0.8)
|
| 431 |
+
|
| 432 |
+
ax.plot(airday_df.index + 1, airday_df['Average'], 'k--', label='Average', linewidth=2.5)
|
| 433 |
+
ax.set_title(f'Cumulative Performance by Air Day ({data_source.replace("_", " ").title()})', fontsize=16)
|
| 434 |
+
ax.set_xlabel('Days Since Release')
|
| 435 |
+
ax.legend(bbox_to_anchor=(1.02, 1), loc='upper left')
|
| 436 |
+
plt.tight_layout()
|
| 437 |
+
plots.append((f'ep_cumul_airday_{data_source}', fig))
|
| 438 |
+
|
| 439 |
+
return plots
|
| 440 |
+
|
| 441 |
+
# --- REPORTING AND ORCHESTRATION ---
|
| 442 |
+
|
| 443 |
+
def generate_executive_summary(self, all_time_metrics, period_metrics, trends, seasonal):
|
| 444 |
+
"""Generates the final executive summary text."""
|
| 445 |
+
summary = f"""# {self.client_name} - Podcast Performance Report
|
| 446 |
+
*Generated on {self.report_date}*
|
| 447 |
+
---
|
| 448 |
+
## 📈 All-Time Performance Summary
|
| 449 |
+
*A high-level overview of the podcast's entire history.*
|
| 450 |
+
|
| 451 |
+
- **Total Plays**: {all_time_metrics.get('total_plays', 0):,}
|
| 452 |
+
- **Total Streams**: {all_time_metrics.get('total_streams', 0):,}
|
| 453 |
+
- **Total Episodes**: {all_time_metrics.get('total_episodes', 0)}
|
| 454 |
+
- **Most Recent Follower Count**: {all_time_metrics.get('current_followers', 0):,}
|
| 455 |
+
- **Median Streams per Episode**: {all_time_metrics.get('median_streams_per_episode', 0):,.0f}
|
| 456 |
+
- **Performance Benchmark (Top 25% of Episodes)**: > {all_time_metrics.get('performance_benchmark', 0):,.0f} streams
|
| 457 |
+
---
|
| 458 |
+
## 📊 Performance for Selected Period: {self.date_range_str}
|
| 459 |
+
*A detailed analysis of performance within the specified date range.*
|
| 460 |
+
|
| 461 |
+
### Key Performance Indicators (Period)
|
| 462 |
+
- **Total Plays in Period**: {period_metrics.get('total_plays', 0):,}
|
| 463 |
+
- **Total Streams in Period**: {period_metrics.get('total_streams', 0):,}
|
| 464 |
+
- **Average Daily Plays**: {period_metrics.get('avg_daily_plays', 0):,.0f}
|
| 465 |
+
- **Engagement Rate (Streams/Plays)**: {period_metrics.get('engagement_percentage', 0):.1f}%
|
| 466 |
+
- **Performance Benchmark (Top 25% of Episodes in Period)**: > {period_metrics.get('performance_benchmark_period', 0):,.0f} streams
|
| 467 |
+
"""
|
| 468 |
+
if trends:
|
| 469 |
+
summary += f"""
|
| 470 |
+
### Growth Trends (Comparison of 30-Day Sub-periods)
|
| 471 |
+
- **Plays Growth (Median)**: {trends.get('plays_growth_rate_median', 0):+.1f}%
|
| 472 |
+
- **Followers Gained**: {trends.get('followers_gained', 0):+,}
|
| 473 |
+
- **Follower Growth Rate**: {trends.get('follower_growth_rate', 0):+.1f}% (vs. prior period)
|
| 474 |
+
"""
|
| 475 |
+
if seasonal:
|
| 476 |
+
summary += f"""
|
| 477 |
+
### Listening Patterns (Period)
|
| 478 |
+
- **Best Day for Plays**: {seasonal.get('best_day')}
|
| 479 |
+
- **Worst Day for Plays**: {seasonal.get('worst_day')}
|
| 480 |
+
- **Weekly Listening Consistency**: {seasonal.get('weekly_consistency', 0):.1f}%
|
| 481 |
+
"""
|
| 482 |
+
summary += "\n### Audience Insights (All-Time)\n"
|
| 483 |
+
if 'geo' in self.all_time_data:
|
| 484 |
+
summary += f"- **Primary Market**: {self.all_time_data['geo'].loc[0, 'Geo']} ({self.all_time_data['geo'].loc[0, 'Percent of Plays'] * 100:.1f}% of plays)\n"
|
| 485 |
+
if 'apps' in self.all_time_data:
|
| 486 |
+
summary += f"- **Platform Mix**: {self._get_platform_share('Spotify'):.1f}% Spotify, {self._get_platform_share('Apple Podcasts'):.1f}% Apple Podcasts\n"
|
| 487 |
+
|
| 488 |
+
summary += "\n## 🏆 Top 5 Performing Episodes (All-Time)\n"
|
| 489 |
+
ep_data = self.all_time_data.get('episodes')
|
| 490 |
+
if ep_data is not None:
|
| 491 |
+
for i, (_, row) in enumerate(ep_data.nlargest(5, 'Streams & Downloads').iterrows(), 1):
|
| 492 |
+
summary += f"{i}. **{row['Episode Title'][:60]}...**\n {row['Streams & Downloads']:,} streams | {row['Publish Date']:%B %Y}\n\n"
|
| 493 |
+
return summary
|
| 494 |
+
|
| 495 |
+
def run_full_analysis(self, uploaded_episode_files, episodes_in_period, gemini_api_key=None):
|
| 496 |
+
"""Orchestrates the entire analysis and report generation process."""
|
| 497 |
+
self.gemini_api_key = gemini_api_key
|
| 498 |
+
print("\n" + "="*60 + "\n🚀 STARTING FULL ANALYSIS & REPORT GENERATION\n" + "="*60)
|
| 499 |
+
self.load_and_match_episode_csvs(uploaded_episode_files, episodes_in_period)
|
| 500 |
+
all_time_metrics = self.calculate_key_metrics(use_all_time=True)
|
| 501 |
+
period_metrics = self.calculate_key_metrics(use_all_time=False)
|
| 502 |
+
trends = self.analyze_growth_trends()
|
| 503 |
+
seasonal = self.analyze_seasonal_patterns()
|
| 504 |
+
summary = self.generate_executive_summary(all_time_metrics, period_metrics, trends, seasonal)
|
| 505 |
+
print("\n" + "="*60 + "\n📋 EXECUTIVE SUMMARY\n" + "="*60)
|
| 506 |
+
print(summary)
|
| 507 |
+
all_plots = self.generate_all_visualizations() + self.generate_episode_specific_plots()
|
| 508 |
+
print("\n✅ Analysis Complete.")
|
| 509 |
+
return summary, all_plots
|
| 510 |
+
|
| 511 |
+
|
| 512 |
+
def process_uploaded_files(files):
|
| 513 |
+
"""Process uploaded files and return file content dictionary."""
|
| 514 |
+
file_contents = {}
|
| 515 |
+
for file in files:
|
| 516 |
+
if file is not None:
|
| 517 |
+
# Read file content
|
| 518 |
+
content = file.read()
|
| 519 |
+
if isinstance(content, bytes):
|
| 520 |
+
content = content.decode('utf-8')
|
| 521 |
+
file_contents[file.name] = content
|
| 522 |
+
return file_contents
|
| 523 |
+
|
| 524 |
+
|
| 525 |
+
def run_podcast_analysis(client_name, date_from, date_to, gemini_api_key, *uploaded_files):
|
| 526 |
+
"""Main function to run the podcast analysis with Gradio inputs."""
|
| 527 |
+
try:
|
| 528 |
+
print(f"🎙️ Starting analysis for: {client_name}")
|
| 529 |
+
print(f"📅 Date range: {date_from} to {date_to}")
|
| 530 |
+
|
| 531 |
+
# Process uploaded files
|
| 532 |
+
all_files = [f for f in uploaded_files if f is not None]
|
| 533 |
+
if not all_files:
|
| 534 |
+
return "❌ Error: No files uploaded. Please upload the required CSV files.", []
|
| 535 |
+
|
| 536 |
+
file_contents = process_uploaded_files(all_files)
|
| 537 |
+
print(f"📁 Processed {len(file_contents)} files")
|
| 538 |
+
|
| 539 |
+
# Separate general files from episode-specific files
|
| 540 |
+
file_patterns = {
|
| 541 |
+
'time_series': 'OnSpotify',
|
| 542 |
+
'episodes': 'EpisodeRankings',
|
| 543 |
+
'geo': 'GeoLocation',
|
| 544 |
+
'apps': 'PlaysByApp',
|
| 545 |
+
'devices': 'PlaysByDevice',
|
| 546 |
+
'streams': 'StreamsAndDownloads'
|
| 547 |
+
}
|
| 548 |
+
|
| 549 |
+
general_files = {}
|
| 550 |
+
episode_files = {}
|
| 551 |
+
|
| 552 |
+
for filename, content in file_contents.items():
|
| 553 |
+
is_general = False
|
| 554 |
+
for file_type, pattern in file_patterns.items():
|
| 555 |
+
if pattern in filename and not any(ep_pattern in filename for ep_pattern in ['episode', 'Episode']):
|
| 556 |
+
general_files[file_type] = io.StringIO(content)
|
| 557 |
+
is_general = True
|
| 558 |
+
break
|
| 559 |
+
|
| 560 |
+
if not is_general:
|
| 561 |
+
episode_files[filename] = content
|
| 562 |
+
|
| 563 |
+
if len(general_files) < 2: # At minimum need OnSpotify and EpisodeRankings
|
| 564 |
+
return "❌ Error: Missing required general files. Please ensure you upload OnSpotify and EpisodeRankings CSV files.", []
|
| 565 |
+
|
| 566 |
+
# Initialize analyzer
|
| 567 |
+
analyzer = ComprehensivePodcastReport(client_name)
|
| 568 |
+
analyzer.load_general_data(general_files)
|
| 569 |
+
|
| 570 |
+
# Set date range
|
| 571 |
+
if date_to:
|
| 572 |
+
end_date = pd.to_datetime(date_to)
|
| 573 |
+
else:
|
| 574 |
+
end_date = get_now()
|
| 575 |
+
|
| 576 |
+
if date_from:
|
| 577 |
+
if isinstance(date_from, str) and date_from.isdigit():
|
| 578 |
+
# If it's a number of days
|
| 579 |
+
start_date = end_date - timedelta(days=int(date_from))
|
| 580 |
+
else:
|
| 581 |
+
start_date = pd.to_datetime(date_from)
|
| 582 |
+
else:
|
| 583 |
+
# Use earliest episode date if no start date provided
|
| 584 |
+
start_date = analyzer.all_time_data['episodes']['Publish Date'].min()
|
| 585 |
+
|
| 586 |
+
analyzer.filter_data_by_date(start_date, end_date)
|
| 587 |
+
|
| 588 |
+
# Identify episodes in period
|
| 589 |
+
episodes_in_period = analyzer.identify_and_prompt_for_episodes()
|
| 590 |
+
|
| 591 |
+
# Run analysis
|
| 592 |
+
summary, plots = analyzer.run_full_analysis(episode_files, episodes_in_period, gemini_api_key)
|
| 593 |
+
|
| 594 |
+
# Convert plots to images for Gradio
|
| 595 |
+
plot_images = []
|
| 596 |
+
for plot_name, fig in plots:
|
| 597 |
+
# Save figure to temporary file
|
| 598 |
+
temp_file = tempfile.NamedTemporaryFile(delete=False, suffix='.png')
|
| 599 |
+
fig.savefig(temp_file.name, dpi=150, bbox_inches='tight')
|
| 600 |
+
plt.close(fig) # Close the figure to free memory
|
| 601 |
+
plot_images.append(temp_file.name)
|
| 602 |
+
|
| 603 |
+
return summary, plot_images
|
| 604 |
+
|
| 605 |
+
except Exception as e:
|
| 606 |
+
import traceback
|
| 607 |
+
error_msg = f"❌ Error during analysis: {str(e)}\n\nTraceback:\n{traceback.format_exc()}"
|
| 608 |
+
print(error_msg)
|
| 609 |
+
return error_msg, []
|
| 610 |
+
|
| 611 |
+
|
| 612 |
+
# Create Gradio Interface
|
| 613 |
+
def create_gradio_interface():
|
| 614 |
+
"""Create the Gradio interface for the podcast analytics tool."""
|
| 615 |
+
|
| 616 |
+
with gr.Blocks(title="Valuebell Podcast Analytics", theme=gr.themes.Soft()) as demo:
|
| 617 |
+
gr.HTML("""
|
| 618 |
+
<div style="text-align: center; margin-bottom: 30px;">
|
| 619 |
+
<h1>🎙️ Valuebell Podcast Analytics Dashboard</h1>
|
| 620 |
+
<p style="font-size: 18px; color: #666;">
|
| 621 |
+
Upload your podcast CSV files to generate comprehensive performance reports
|
| 622 |
+
</p>
|
| 623 |
+
</div>
|
| 624 |
+
""")
|
| 625 |
+
|
| 626 |
+
with gr.Row():
|
| 627 |
+
with gr.Column(scale=1):
|
| 628 |
+
gr.HTML("<h3>📋 Configuration</h3>")
|
| 629 |
+
|
| 630 |
+
client_name = gr.Textbox(
|
| 631 |
+
label="Client/Podcast Name",
|
| 632 |
+
placeholder="Enter the podcast name...",
|
| 633 |
+
value="My Podcast"
|
| 634 |
+
)
|
| 635 |
+
|
| 636 |
+
with gr.Row():
|
| 637 |
+
date_from = gr.Textbox(
|
| 638 |
+
label="Start Date",
|
| 639 |
+
placeholder="YYYY-MM-DD or number of days (e.g., '60' for last 60 days)",
|
| 640 |
+
value="60"
|
| 641 |
+
)
|
| 642 |
+
date_to = gr.Textbox(
|
| 643 |
+
label="End Date (optional)",
|
| 644 |
+
placeholder="YYYY-MM-DD (leave empty for today)"
|
| 645 |
+
)
|
| 646 |
+
|
| 647 |
+
gemini_api_key = gr.Textbox(
|
| 648 |
+
label="Gemini API Key (optional)",
|
| 649 |
+
placeholder="For Hebrew title translation...",
|
| 650 |
+
type="password"
|
| 651 |
+
)
|
| 652 |
+
|
| 653 |
+
gr.HTML("<h3>📁 File Uploads</h3>")
|
| 654 |
+
gr.HTML("""
|
| 655 |
+
<div style="background-color: #f0f8ff; padding: 15px; border-radius: 8px; margin-bottom: 15px;">
|
| 656 |
+
<h4>Required Files:</h4>
|
| 657 |
+
<ul>
|
| 658 |
+
<li><strong>OnSpotify</strong> CSV (daily plays data)</li>
|
| 659 |
+
<li><strong>EpisodeRankings</strong> CSV (episode performance data)</li>
|
| 660 |
+
</ul>
|
| 661 |
+
<h4>Optional Files:</h4>
|
| 662 |
+
<ul>
|
| 663 |
+
<li><strong>StreamsAndDownloads</strong> CSV (all platforms data)</li>
|
| 664 |
+
<li><strong>GeoLocation</strong> CSV (geographic data)</li>
|
| 665 |
+
<li><strong>PlaysByApp</strong> CSV (platform distribution)</li>
|
| 666 |
+
<li><strong>PlaysByDevice</strong> CSV (device distribution)</li>
|
| 667 |
+
<li>Individual episode CSV files (for detailed episode analysis)</li>
|
| 668 |
+
</ul>
|
| 669 |
+
</div>
|
| 670 |
+
""")
|
| 671 |
+
|
| 672 |
+
# Multiple file upload components
|
| 673 |
+
files = []
|
| 674 |
+
for i in range(20): # Allow up to 20 file uploads
|
| 675 |
+
file_upload = gr.File(
|
| 676 |
+
label=f"Upload CSV File {i+1}" if i < 6 else None,
|
| 677 |
+
file_types=[".csv"],
|
| 678 |
+
visible=i < 6 # Show first 6 by default
|
| 679 |
+
)
|
| 680 |
+
files.append(file_upload)
|
| 681 |
+
|
| 682 |
+
analyze_btn = gr.Button("🚀 Generate Analytics Report", variant="primary", size="lg")
|
| 683 |
+
|
| 684 |
+
with gr.Column(scale=2):
|
| 685 |
+
gr.HTML("<h3>📊 Results</h3>")
|
| 686 |
+
|
| 687 |
+
summary_output = gr.Markdown(
|
| 688 |
+
label="Executive Summary",
|
| 689 |
+
value="Upload files and click 'Generate Analytics Report' to see results..."
|
| 690 |
+
)
|
| 691 |
+
|
| 692 |
+
plots_output = gr.Gallery(
|
| 693 |
+
label="Performance Visualizations",
|
| 694 |
+
show_label=True,
|
| 695 |
+
elem_id="plots-gallery",
|
| 696 |
+
columns=2,
|
| 697 |
+
rows=3,
|
| 698 |
+
height="auto"
|
| 699 |
+
)
|
| 700 |
+
|
| 701 |
+
# Set up the analysis function
|
| 702 |
+
analyze_btn.click(
|
| 703 |
+
fn=run_podcast_analysis,
|
| 704 |
+
inputs=[client_name, date_from, date_to, gemini_api_key] + files,
|
| 705 |
+
outputs=[summary_output, plots_output],
|
| 706 |
+
show_progress=True
|
| 707 |
+
)
|
| 708 |
+
|
| 709 |
+
gr.HTML("""
|
| 710 |
+
<div style="text-align: center; margin-top: 30px; padding: 20px; background-color: #f8f9fa; border-radius: 8px;">
|
| 711 |
+
<h4>💡 Tips for Best Results:</h4>
|
| 712 |
+
<ul style="text-align: left; display: inline-block;">
|
| 713 |
+
<li>Ensure your CSV files follow Spotify for Creators naming conventions</li>
|
| 714 |
+
<li>For Hebrew podcasts, provide a Gemini API key for title translation</li>
|
| 715 |
+
<li>Include episode-specific CSV files for detailed performance tracking</li>
|
| 716 |
+
<li>Use date ranges that cover complete weeks for better trend analysis</li>
|
| 717 |
+
</ul>
|
| 718 |
+
</div>
|
| 719 |
+
""")
|
| 720 |
+
|
| 721 |
+
return demo
|
| 722 |
+
|
| 723 |
+
|
| 724 |
+
if __name__ == "__main__":
|
| 725 |
+
# Create and launch the Gradio interface
|
| 726 |
+
demo = create_gradio_interface()
|
| 727 |
+
demo.launch(
|
| 728 |
+
share=True,
|
| 729 |
+
server_name="0.0.0.0",
|
| 730 |
+
server_port=7860,
|
| 731 |
+
show_error=True
|
| 732 |
+
)
|