Merge pull request #93 from jacobp24/sue_13

Sue 13

.github/workflows/build_test.yml

@@ -89,10 +89,12 @@ jobs:
       # If there are any other steps in order for your tests to
       # run successfully, you can add those steps here!
 
-      # Next step: run pylint. Anything less than 10/10 will fail.
-      #- name: Lint with pylint
-      #  run: |
-      #    pylint bookworm/**/*.py
+    #  # Next step: run pylint. Anything less than 10/10 will fail.
+    #   - name: Lint with pylint
+    #     run: |
+    #     pylint bookworm/*.py
+    #     pylint bookworm/**/*.py
+
 
       # Next step: run the unit tests with code coverage.
       - name: Unit tests

bookworm/__init__.py

@@ -1 +1 @@
-# EMPTY FILE
+# EMPTY FILE

bookworm/app.py

@@ -1,8 +1,32 @@
-import base64
-import streamlit as st
-import streamlit.components.v1 as components
+""" 
+UI Module for Bookworm App
+
+FUNCTIONS
+========
+display_avg_ratings_slider():
+    Displays average ratings slider; returns input.  
+
+display_num_ratings_slider():
+    Displays slider for number of ratings; returns input. 
+
+display_search_mode_ui():
+    Displays text box for user to enter desired search method; returns input. 
+
+display_search_value_ui(search_mode):
+    Displays text box for user to enter query to search; retrieves user input. 
+
+display_genre_dropdown():
+    Displays drop down menu for genre selection; retrieves value; returns input.
+
+main()
+    Displays UI; gathers user feedback; executes serach.
+    
+"""
 
 
+import base64
+import streamlit as st
+#import streamlit.components.v1 as components
 try:
     from search_wrapper import search_wrapper
 except ImportError:
@@ -49,18 +73,38 @@ def local_css(file_name):
 
 # DEFINE EACH UI ELEMENT AS A SEPARATE FUNCTION
 def display_avg_ratings_slider():
+    """ 
+    Displays average ratings slider, values 0 to 10.  Returns user input.  
+    
+        Return value
+            User's selected average ratings, as a float. 
+    """
     return st.slider("Exclude Books with Average Ratings Lower than:",
                      min_value=0.0, max_value=10.0,
                      value=0.0, step=0.5, key="Ave. Ratings Slider",
                      help="Set the minimum average rating.")
 
 def display_num_ratings_slider():
+    """ 
+    Displays slider for number of ratings; returns user input. 
+    
+        Return value
+            User's selected number of ratings, as an int.  
+    
+    """
     return st.slider("Exclude Books that have been rated by fewer than:",
                      min_value=0, max_value=50,
                     value=0, step=1, key="Num. Ratings Slider",
                     help="Set the minimum number of ratings.")
 
 def display_search_mode_ui():
+    """ 
+    Display text box for user to enter desired search method; returns input.
+    
+        Return value
+            User's search mode selection, as a string. 
+    """
+
     help_text_string = "Choose how you want to prioritize your search."
     selection = st.selectbox("Search Mode", [None] + SEARCH_MODES,
                              help=help_text_string, key="search_mode")
@@ -74,37 +118,52 @@ def display_search_mode_ui():
     return search_mode
 
 def display_search_value_ui(search_mode):
+    """ Display text box for user to enter query to search; returns input. 
+    
+        Return value
+            User's search query, as a string. 
+    """
+
     if search_mode == "Genre":
         return display_genre_dropdown()
-    else:
-        display_str = search_mode
-        if display_str in ["Author1", "Author2"]:
-            display_str = display_str[:-1]
-        return st.text_input(f"Input your favorite {display_str}",
+    display_str = search_mode
+    if display_str in ["Author1", "Author2"]:
+        display_str = display_str[:-1]
+    return st.text_input(f"Input your favorite {display_str}",
                              key="search_val")
 
 def display_genre_dropdown():
+    """ 
+    Displays drop down menu for genre selection; returns user input.
+    
+        Return value
+            User's genre selection as a string. 
+    """
     help_text_string = "Select your favorite genre."
     genre_pick = st.selectbox("Favorite Genre", [None] + GENRES,
                               help=help_text_string)
     if genre_pick == "Other":
         return st.text_input("Describe your favorite genre", key="other_genre")
-    else:
-        return genre_pick
-
-def display_search_button():
+    return genre_pick
+
+def display_search_button(disabled=False):
+    """ 
+    Displays button to initate search. 
+    
+        Return value
+            Boolean indicating whether user has clicked search. 
+    """
     return st.button("Search Now", key="search_now",
                      help="Click to initiate search.", type="primary",
-                     disabled=False, use_container_width=False)
+                     disabled=disabled, use_container_width=False)
 
-def execute_query(search_mode, search_value, min_ave_rating, min_num_ratings):
-    st.write(f"Searching for books using {search_mode}, value: {search_value}, "
-             f"min average rating: {min_ave_rating}, "
-             f"min number of ratings: {min_num_ratings}") 
 
 def main():
-    # Display header banner with stock image of books
+    """ 
+    Displays UI; gathers user feedback; executes serach.
+    """
 
+    # Display header banner with stock image of books
     st.image("images/books_banner.png", use_column_width=True)
 
     title_image = "images/butterfly.png"
@@ -113,7 +172,8 @@ def main():
     st.markdown(
         f"""
         <div class="container">
-            <img class="title-img" src="data:image/png;base64,{base64.b64encode(open(title_image, "rb").read()).decode()}">
+            <img class="title-img" src="data:image/png;base64,
+            {base64.b64encode(open(title_image, "rb").read()).decode()}">
             <p class="title-text">The Bookish Butterfly</p>
         </div>
         """,
@@ -122,7 +182,7 @@ def main():
 
 
     # Add introductory text
-    st.write("Welcome to The Bookish Butterfly! An literary guide designed for"
+    st.write("Welcome to The Bookish Butterfly! A literary guide designed for"
               "bookworms, aiding in the exploration of new books with tailored"
               "preferences. Simply choose how you want to prioritize your" 
               "search, input your favorite book, author, plot, or genre. "
@@ -138,16 +198,21 @@ def main():
     min_ave_rating = display_avg_ratings_slider()
     min_num_ratings = display_num_ratings_slider()
 
-    search_button = display_search_button()
+
 
     if search_val not in ["", None]:
-        st.write("Click 'Search Now' when ready.")
-        if search_button:
-            try:
-                results = search_wrapper(search_mode, search_val, min_ave_rating, min_num_ratings)
-                col_to_show = ["book_title", "author", "Book-Rating", "RatingCount"]
-                st.write(results[col_to_show])
-            except ValueError as e:
-                st.write(f"{str(e)}")
+        search_button = display_search_button()
+        if not search_button:
+            st.write("Click 'Search Now' when ready.")
+        else:
+            with st.spinner('Searching...'):
+                try:
+                    results = search_wrapper(search_mode, search_val,
+                                             min_ave_rating, min_num_ratings)
+                    col_to_show = ["book_title", "author", "Book-Rating",
+                                   "RatingCount"]
+                    st.write(results[col_to_show])
+                except ValueError as e:
+                    st.write(f"{str(e)}")
 
 main()

bookworm/search.py

@@ -42,7 +42,6 @@
 """
 
 import os
-
 import ast
 import numpy as np
 from sklearn.feature_extraction.text import TfidfVectorizer
@@ -151,7 +150,7 @@ def query_to_index(df, query, columns, vectorizer=None, num_idx=1):
         """ 
         Maps query to the closest book index via keyword search.
         
-        Maps query based to the closes book in dataframe (df) 
+        Maps query based to the closest book in dataframe (df) 
         based on keyword search using given vectorizer(default
         is TfidfVectorizer). Then returns the index of that book
         in the dataframe.  

bookworm/search_wrapper.py

@@ -14,7 +14,7 @@
 filter_ratings(results, min_ave_ratings, min_num_rating)
     Filters serach results by user ratings prefrences. 
 
-select_search(df, search_mode, search_value, min_ave_rating, 
+select_search(search_mode, search_value, min_ave_rating, 
                   min_num_ratings, num_book=10)
     Selects and implements search based on user search mode.
 
@@ -53,6 +53,19 @@ def assemble_data(path1, path2, path3, path4):
     df = pd.concat([df1, df2, df3, df4], ignore_index=True)
     return df
 
+def assemble_embeddings_data():
+    """
+    Functions that assembles the data with embeddings
+    """
+    # Create file paths
+
+    path_root = "data/complete_w_embeddings/complete_w_embeddings.csv"
+    path1 = path_root + "_part_1.csv"
+    path2 = path_root + "_part_2.csv"
+    path3 = path_root + "_part_3.csv"
+    path4 = path_root + "_part_4.csv"
+    return assemble_data(path1, path2, path3, path4)
+
 # Filter
 def filter_ratings(results, min_ave_ratings, min_num_rating):
 
@@ -87,13 +100,11 @@ def filter_ratings(results, min_ave_ratings, min_num_rating):
         results_filtered = subset_df
     return results_filtered
 
-def select_search(df, search_mode, search_value, num_books=10):
+def select_search(search_mode, search_value, num_books=10):
     """
     Selects and implements search based on user search mode.
 
     Parameters:
-        df: pandas.DataFrame
-            The dataframe to perform the search on.
         search_mode: str
             The mode of search ('Author2', 'Title', 'Plot', 'Genre').
         search_value: str
@@ -103,16 +114,19 @@ def select_search(df, search_mode, search_value, num_books=10):
 
     Returns:
         pandas.DataFrame
-            A dataframe of filtered search results.
+            A dataframe of search results.
     """
 
     if search_mode == "Author2":
+        df = pd.read_csv("data/complete_w_ratings.csv")
         results = search.author2_search(df, search_value,
                                         num_books=max(num_books * 2, 20))
     elif search_mode == "Title":
+        df = assemble_embeddings_data()
         results = search.semantic_search(df, search_value, ["book_title"],
                                          num_books=max(num_books * 2, 20))
     elif search_mode == "Plot":
+        df = assemble_embeddings_data()
         results = search.plot_semantic_search(df, search_value,
                                               num_books=max(num_books * 2, 20))
     elif search_mode == "Genre":
@@ -122,7 +136,9 @@ def select_search(df, search_mode, search_value, num_books=10):
             genre_df = pd.read_csv("data/genre.csv")
         results = search.genre_search(genre_df, search_value,
                                       num_books=max(num_books * 2, 20))
+
     else:  # Default to keyword search on all columns for other modes
+        df = pd.read_csv("data/complete_w_ratings.csv")
         results = search.keyword_search(df, search_value,
                                         num_books=max(num_books * 2, 20))
 
@@ -145,24 +161,9 @@ def search_wrapper(search_mode, search_value, min_ave_rating,
     Returns
         A dataframe of filtered search results. 
     """
-    # assemble data
-    try:
-        path_root = "bookworm/data/complete_w_embeddings/complete_w_embeddings.csv"
-        path1 = path_root + "_part_1.csv"
-        path2 = path_root + "_part_2.csv"
-        path3 = path_root + "_part_3.csv"
-        path4 = path_root + "_part_4.csv"
-        df = assemble_data(path1, path2, path3, path4)
-    except FileNotFoundError:
-        path_root = "data/complete_w_embeddings/complete_w_embeddings.csv"
-        path1 = path_root + "_part_1.csv"
-        path2 = path_root + "_part_2.csv"
-        path3 = path_root + "_part_3.csv"
-        path4 = path_root + "_part_4.csv"
-        df = assemble_data(path1, path2, path3, path4)
 
     # search
-    results = select_search(df, search_mode, search_value, num_books)
+    results = select_search(search_mode, search_value, num_books)
 
     #filter
     results_filtered = filter_ratings(results, min_ave_rating, min_num_ratings)

bookworm/tests/test_app.py

@@ -30,10 +30,16 @@
 
 import pandas as pd
 
-
-from app import main, display_avg_ratings_slider, display_num_ratings_slider, \
-                display_search_mode_ui, display_search_value_ui, \
-                display_genre_dropdown, display_search_button, execute_query
+try:
+    from app import (main, display_avg_ratings_slider,
+                     display_num_ratings_slider, display_search_mode_ui,
+                     display_search_value_ui, display_genre_dropdown,
+                     display_search_button)
+except ImportError:
+    from bookworm.app import (main, display_avg_ratings_slider,
+                     display_num_ratings_slider, display_search_mode_ui,
+                     display_search_value_ui, display_genre_dropdown,
+                     display_search_button)
 
 
 class TestStreamlitUI(unittest.TestCase):
@@ -103,13 +109,13 @@ def test_display_search_button(self):
             result = display_search_button()
             self.assertTrue(result)
 
-    def test_execute_query(self):
-        """Test execute_query function."""
-        with patch('streamlit.write') as mock_write:
-            execute_query("Title", "The Great Gatsby", 8.0, 20)
-            mock_write.assert_called_once_with(
-                "Searching for books using Title, value: The Great Gatsby, "
-                "min average rating: 8.0, min number of ratings: 20")
+    # def test_execute_query(self):
+    #     """Test execute_query function."""
+    #     with patch('streamlit.write') as mock_write:
+    #         execute_query("Title", "The Great Gatsby", 8.0, 20)
+    #         mock_write.assert_called_once_with(
+    #             "Searching for books using Title, value: The Great Gatsby, "
+    #             "min average rating: 8.0, min number of ratings: 20")
 
 
 if __name__ == '__main__':