app.py

@@ -2,13 +2,9 @@ from pathlib import Path
 from typing import List
 from shiny import App, ui, Inputs, Outputs, Session
 from shiny.types import NavSetArg
-from src import mod_welcome, mod_searchable, mod_topics
+from src import mod_welcome, mod_searchable
 from src.util import load_html_str_from_file
 
-
-# by importing this module, the tweets are loaded into the tweet_store variable at program start
-import src.data_loader
-
 import os
 
 
@@ -19,9 +15,7 @@ def nav_controls() -> List[NavSetArg]:
     return [
         ui.nav(ui.h5("Intro"), mod_welcome.welcome_ui("intro"), value="intro"),
         ui.nav(ui.h5("Analyse"), "Analyse"),
-        ui.nav(ui.h5("Suchmaschine"), mod_searchable.searchable_ui(
+        ui.nav(ui.h5("Suchmaschine"), mod_searchable.searchable_ui("search_engine"), value="search_engine"),
-            "search_engine"), value="search_engine"),
-        ui.nav(ui.h5("Topics"), mod_topics.topics_ui("topics"), value="topics"),
         ui.nav_control(
             ui.a(
                 ui.h5("AG-Link"),
@@ -66,7 +60,6 @@ app_ui = ui.page_navbar(
 def server(input: Inputs, output: Outputs, session: Session):
     mod_welcome.welcome_server("intro")
     mod_searchable.searchable_server("search_engine")
-    mod_topics.topics_server("topics")
 
 
 static_dir = Path(__file__).parent / "www"

src/data_loader.py

@@ -1,26 +0,0 @@
-import pandas as pd
-from sklearn.feature_extraction.text import TfidfVectorizer
-import pickle
-
-
-class TweetStore():
-
-    tweets_path: str = "data/tweets_all_combined.csv"
-    tfidf_matrix_path = "data/tfidf_matrix.pckl"
-    tfidf_vectorizer_path = "data/tfidf_vectorizer.pckl"
-
-    def __init__(self):
-        print("Loading tweets from dataframe")
-        self.tweets = pd.read_csv(self.tweets_path)
-
-        print("Loading tfidf from file")
-        self.tfidf_matrix = None
-        with open(self.tfidf_matrix_path, "rb") as f:
-            self.tfidf_matrix = pickle.load(f)
-
-        self.tfidf_vectorizer: TfidfVectorizer = None
-        with open(self.tfidf_vectorizer_path, "rb") as f:
-            self.tfidf_vectorizer = pickle.load(f)
-
-
-tweet_store = TweetStore()

src/mod_searchable.py

@@ -1,12 +1,15 @@
 from shiny import module, ui, render, Inputs, Outputs, Session
+from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.metrics.pairwise import cosine_similarity
 import pandas as pd
 import numpy as np
+import pickle
 import re
 
-from src.data_loader import tweet_store
+tfidf_matrix_path = "data/tfidf_matrix.pckl"
-
+tfidf_vectorizer_path = "data/tfidf_vectorizer.pckl"
 relevance_score_path = "data/tweet_relevance.json"
+tweets_path = "data/tweets_all_combined.csv"
 
 reply_html_svg = '<svg width="18px" height="18px" viewBox="0 0 24 24" aria-hidden="true"><g><path d="M1.751 10c0-4.42 3.584-8 8.005-8h4.366c4.49 0 8.129 3.64 8.129 8.13 0 2.96-1.607 5.68-4.196 7.11l-8.054 4.46v-3.69h-.067c-4.49.1-8.183-3.51-8.183-8.01zm8.005-6c-3.317 0-6.005 2.69-6.005 6 0 3.37 2.77 6.08 6.138 6.01l.351-.01h1.761v2.3l5.087-2.81c1.951-1.08 3.163-3.13 3.163-5.36 0-3.39-2.744-6.13-6.129-6.13H9.756z"></path></g></svg>'
 retweet_html_svg = '<svg width="18px" height="18px" viewBox="0 0 24 24" aria-hidden="true"><g><path d="M4.5 3.88l4.432 4.14-1.364 1.46L5.5 7.55V16c0 1.1.896 2 2 2H13v2H7.5c-2.209 0-4-1.79-4-4V7.55L1.432 9.48.068 8.02 4.5 3.88zM16.5 6H11V4h5.5c2.209 0 4 1.79 4 4v8.45l2.068-1.93 1.364 1.46-4.432 4.14-4.432-4.14 1.364-1.46 2.068 1.93V8c0-1.1-.896-2-2-2z"></path></g></svg>'
@@ -28,21 +31,31 @@ def replace_hastag(match):
     return f'<a href="https://twitter.com/search?q=%23{name}" style="text-decoration:none">{hashtag}</a>'
 
 
+print("Loading data from storage")
+tweets = pd.read_csv(tweets_path)
 relevance_score = pd.read_csv(relevance_score_path)
 
+tfidf_matrix = None
+with open(tfidf_matrix_path, "rb") as f:
+    tfidf_matrix = pickle.load(f)
 
-tweet_store.tweets["relevance_score"] = relevance_score["relevance_score"]
+tfidf_vectorizer: TfidfVectorizer = None
-tweet_store.tweets = tweet_store.tweets.drop(["user_id", "measured_at"], axis=1)
+with open(tfidf_vectorizer_path, "rb") as f:
+    tfidf_vectorizer = pickle.load(f)
+
+
+tweets["relevance_score"] = relevance_score["relevance_score"]
+tweets = tweets.drop(["user_id", "measured_at"], axis=1)
 
 
 def search_query(query: str, limit: int = 5, sorting_method: str = "score") -> (pd.DataFrame, int):
-    query_vec = tweet_store.tfidf_vectorizer.transform([query])
+    query_vec = tfidf_vectorizer.transform([query])
-    similarity = cosine_similarity(query_vec, tweet_store.tfidf_matrix).flatten()
+    similarity = cosine_similarity(query_vec, tfidf_matrix).flatten()
 
     filtered = np.where(similarity != 0)[0]
     indices = np.argsort(-similarity[filtered])
     correct_indices = filtered[indices]
-    result = tweet_store.tweets.iloc[correct_indices]
+    result = tweets.iloc[correct_indices]
 
     if not len(result):
         return None, 0
@@ -68,13 +81,10 @@ def searchable_ui():
         ui.h2("Tweet Suchmaschine"),
         ui.HTML("<hr>"),
         ui.row(
-            ui.column(6, ui.input_text("search_input", "Suche",
+            ui.column(6, ui.input_text("search_input", "Suche", placeholder="Gib Suchterm ein", value="Leipzig", width="100%")),
-                      placeholder="Gib Suchterm ein", value="Leipzig", width="100%")),
             ui.column(3,
-                      ui.input_select("sorting_method", "Sortierung", {
+                      ui.input_select("sorting_method", "Sortierung", {"score": "Relevanz", "date_new": "Neuste Zuerst", "date_old": "Älteste Zuerst"}, selected="score", selectize=True, width="12em"),
-                                      "score": "Relevanz", "date_new": "Neuste Zuerst", "date_old": "Älteste Zuerst"}, selected="score", selectize=True, width="12em"),
+                      ui.input_select("tweet_count", "Ergebnisse", {"5": "5", "20": "20", "50": "50", "all": "alle"}, selected="5", selectize=True, width="12em"),
-                      ui.input_select("tweet_count", "Ergebnisse", {
-                                      "5": "5", "20": "20", "50": "50", "all": "alle"}, selected="5", selectize=True, width="12em"),
                       style="display: flex; flex-direction: column; align-items: center; justify-content: center;"),
             style="justify-content:space-between;"
 
@@ -128,8 +138,7 @@ def searchable_server(input: Inputs, output: Outputs, session: Session):
                     ui.row(
                         ui.column(6, ui.HTML(
                             f"<b>{user_name}</b> <a href='https://twitter.com/{user_handle}' style='text-decoration: none;'>@{user_handle}</a>"), style=style + "padding-top: 1.5em; "),
-                        ui.column(6, ui.p(f"{row['created_at']}"),
+                        ui.column(6, ui.p(f"{row['created_at']}"), style=style + "padding-top: 1.5em;"),
-                                  style=style + "padding-top: 1.5em;"),
                     ),
                     ui.row(
                         ui.column(12, ui.HTML("<hr>"),

src/mod_topics.py

@@ -1,37 +0,0 @@
-from shiny import module, ui, render, Inputs, Outputs, Session
-
-from sklearn.decomposition import NMF
-from src.data_loader import tweet_store
-
-classes = 10
-
-# Fit the NMF model
-nmf = NMF(
-    n_components=classes,
-    random_state=42,
-    init=None,
-    beta_loss="frobenius",
-    alpha_W=0.0,
-    alpha_H="same",
-    l1_ratio=0.0,
-).fit(tweet_store.tfidf_matrix)
-
-
-# TODO: dont do this live -> load the feature_names and values from a pre-calculated list for each day
-tfidf_feature_names = tweet_store.tfidf_vectorizer.get_feature_names_out()
-print(tfidf_feature_names)
-
-
-@ module.ui
-def topics_ui():
-    return ui.div(
-        ui.h2("Tweet Topics"),
-    )
-
-
-@ module.server
-def topics_server(input: Inputs, output: Outputs, session: Session):
-    @ output
-    @ render.ui
-    def searchable_tweet_ui():
-        pass