Merge pull request #49 from DSProjects2024/raagul/prod-fix

Updated file reading logic for prod streamlit

thronetalk-game-of-thrones-summarizer/app.py

@@ -18,11 +18,9 @@
 import time
 import streamlit as st
 import pandas as pd
-#import numpy as np
 import matplotlib.pyplot as plt
-#from wordcloud import WordCloud
 from utils.model import Model
-from utils.visualization_generator import VisualizationGenerator
+from utils.visualization_generator import VisualizationGenerator, read_dataframe
 from utils.data_analysis import DataAnalysis
 import altair as alt
 
@@ -78,7 +76,7 @@ def remove_zeros(lst):
 season_to = int(season_to)
 to_ep_no = int(to_ep_no)
 if submitted:
-    cleaned_data = pd.read_csv(f'{current_directory}/data/ouput_dialogues.csv')
+    cleaned_data = read_dataframe('ouput_dialogues.csv')
     data_analysis = DataAnalysis(cleaned_data)
     top_3_characters = data_analysis.get_top_n_characters(
         from_season=int(season_from),
@@ -104,8 +102,6 @@ def remove_zeros(lst):
         int(to_ep_no)
     )
     line_chart = vg.sentiment_analysis_visualization(characters)
-    line_chart = vg.sentiment_analysis_visualization(characters)
-    print(characters)
     chart = alt.Chart(line_chart).transform_fold(
                     characters, as_=["character name", "value"]
                     ).mark_line(
@@ -144,7 +140,7 @@ def remove_zeros(lst):
             st.subheader(characters[i].capitalize())
             st.pyplot(plots[i])
     st.write("\n")
-    episodes_metadata_for_img_df = pd.read_csv('data/episodes_metadata.csv')
+    episodes_metadata_for_img_df = read_dataframe('episodes_metadata.csv')
     st.subheader(out_text_temp)
     #Summarizer
     def spinner_loading_summary():

thronetalk-game-of-thrones-summarizer/utils/__init__.py

@@ -11,6 +11,6 @@
 
 Use these functions within your Streamlit app to enhance its capabilities.
 """
-from .visualization_generator import VisualizationGenerator
+from .visualization_generator import VisualizationGenerator, read_dataframe
 from .model import Model
 from .data_analysis import DataAnalysis

thronetalk-game-of-thrones-summarizer/utils/visualization_generator.py

@@ -37,13 +37,24 @@
 from nltk.stem import WordNetLemmatizer
 from wordcloud import WordCloud, STOPWORDS
 from sklearn.feature_extraction.text import TfidfVectorizer
+
 nltk.download('punkt')
 nltk.download('wordnet')
 nltk.download('vader_lexicon')
 nltk.download('stopwords')
 nltk.download('omw-1.4')
 
-data = pd.read_csv("data/ouput_dialogues.csv")
+def read_dataframe(file_name):
+    '''Function to read dataframe for different environments. Used for tests
+    and app.py'''
+    file_data = None
+    try:
+        file_data = pd.read_csv(f'data/{file_name}')
+    except FileNotFoundError:
+        file_data = pd.read_csv(f'./thronetalk-game-of-thrones-summarizer/data/{file_name}')
+    return file_data
+
+data = read_dataframe('ouput_dialogues.csv')
 
 class VisualizationGenerator:
     """