Completes search engine for tweets

.gitignore

@@ -160,3 +160,6 @@ cython_debug/
 #  option (not recommended) you can uncomment the following to ignore the entire idea folder.
 #.idea/
 
+
+data/tfidf_matrix.pckl
+data/tfidf_vectorizer.pckl

app.py

@@ -2,7 +2,7 @@ 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
+from src import mod_welcome, mod_searchable
 from src.util import load_html_str_from_file
 
 import os
@@ -13,8 +13,9 @@ footer_html: str = load_html_str_from_file(os.path.join("www", "footer.html"))
 
 def nav_controls() -> List[NavSetArg]:
     return [
-        ui.nav(ui.h5("Intro"), mod_welcome.welcome_ui("Intro"), value="intro"),
+        ui.nav(ui.h5("Intro"), mod_welcome.welcome_ui("intro"), value="intro"),
-        ui.nav(ui.h5("Datensatz Analyse"), "Datensatz Analyse"),
+        ui.nav(ui.h5("Analyse"), "Analyse"),
+        ui.nav(ui.h5("Suchmaschine"), mod_searchable.searchable_ui("search_engine"), value="search_engine"),
         ui.nav_control(
             ui.a(
                 ui.h5("AG-Link"),
@@ -42,7 +43,7 @@ app_ui = ui.page_navbar(
         ),
         align="right",
     ),
-    selected="intro",
+    selected="search_engine",
     fluid=False,
     title=ui.div(ui.img(src="favicon.ico", width="75dpi", height="75dpi"),
                  ui.h1("Copbird")),
@@ -57,7 +58,8 @@ app_ui = ui.page_navbar(
 
 
 def server(input: Inputs, output: Outputs, session: Session):
-    mod_welcome.welcome_server("Intro")
+    mod_welcome.welcome_server("intro")
+    mod_searchable.searchable_server("search_engine")
 
 
 static_dir = Path(__file__).parent / "www"

src/mod_searchable.py

@@ -0,0 +1,174 @@
+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
+
+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>'
+like_html_svg = '<svg width="18px" height="18px" viewBox="0 0 24 24" aria-hidden="true"><g><path d="M16.697 5.5c-1.222-.06-2.679.51-3.89 2.16l-.805 1.09-.806-1.09C9.984 6.01 8.526 5.44 7.304 5.5c-1.243.07-2.349.78-2.91 1.91-.552 1.12-.633 2.78.479 4.82 1.074 1.97 3.257 4.27 7.129 6.61 3.87-2.34 6.052-4.64 7.126-6.61 1.111-2.04 1.03-3.7.477-4.82-.561-1.13-1.666-1.84-2.908-1.91zm4.187 7.69c-1.351 2.48-4.001 5.12-8.379 7.67l-.503.3-.504-.3c-4.379-2.55-7.029-5.19-8.382-7.67-1.36-2.5-1.41-4.86-.514-6.67.887-1.79 2.647-2.91 4.601-3.01 1.651-.09 3.368.56 4.798 2.01 1.429-1.45 3.146-2.1 4.796-2.01 1.954.1 3.714 1.22 4.601 3.01.896 1.81.846 4.17-.514 6.67z"></path></g></svg>'
+quote_count_svg = '<svg width="18px" height="18px" viewBox="0 0 57 57"><g stroke-width="0"></g><g stroke-linecap="round" stroke-linejoin="round"></g><g> <g> <circle cx="18.5" cy="31.5" r="5.5"></circle> <path d="M18.5,38c-3.584,0-6.5-2.916-6.5-6.5s2.916-6.5,6.5-6.5s6.5,2.916,6.5,6.5S22.084,38,18.5,38z M18.5,27c-2.481,0-4.5,2.019-4.5,4.5s2.019,4.5,4.5,4.5s4.5-2.019,4.5-4.5S20.981,27,18.5,27z"></path> </g> <g> <circle cx="35.5" cy="31.5" r="5.5"></circle> <path d="M35.5,38c-3.584,0-6.5-2.916-6.5-6.5s2.916-6.5,6.5-6.5s6.5,2.916,6.5,6.5S39.084,38,35.5,38z M35.5,27c-2.481,0-4.5,2.019-4.5,4.5s2.019,4.5,4.5,4.5s4.5-2.019,4.5-4.5S37.981,27,35.5,27z"></path> </g> <path d="M13,32c-0.553,0-1-0.447-1-1c0-7.72,6.28-14,14-14c0.553,0,1,0.447,1,1s-0.447,1-1,1 c-6.617,0-12,5.383-12,12C14,31.553,13.553,32,13,32z"></path> <path d="M30,32c-0.553,0-1-0.447-1-1c0-7.72,6.28-14,14-14c0.553,0,1,0.447,1,1s-0.447,1-1,1 c-6.617,0-12,5.383-12,12C31,31.553,30.553,32,30,32z"></path> </g></svg>'
+
+link_regex = r"(https?://\S+)"
+hashtag_regex = r"#(\w+)"
+
+
+def replace_link(match):
+    url = match.group(0)
+    return f'<a href="{url}">{url}</a>'
+
+
+def replace_hastag(match):
+    hashtag = match.group(0)
+    name = str(hashtag).removeprefix("#")
+    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)
+
+tfidf_vectorizer: TfidfVectorizer = None
+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 = tfidf_vectorizer.transform([query])
+    similarity = cosine_similarity(query_vec, tfidf_matrix).flatten()
+
+    filtered = np.where(similarity != 0)[0]
+    indices = np.argsort(-similarity[filtered])
+    correct_indices = filtered[indices]
+    result = tweets.iloc[correct_indices]
+
+    if not len(result):
+        return None
+
+    if limit == -1:
+        limit = len(result)
+
+    results = None
+    if sorting_method == "score":
+        overall = (0.6 * result['relevance_score']) * similarity[correct_indices]
+        results = result.loc[overall.sort_values(ascending=False).index].head(limit)
+    elif sorting_method == "date_new":
+        results = result.sort_values(by="created_at", ascending=False).head(limit)
+    elif sorting_method == "date_old":
+        results = result.sort_values(by="created_at", ascending=True).head(limit)
+
+    return results, len(result)
+
+
+@ module.ui
+def searchable_ui():
+    return ui.div(
+        ui.h2("Tweet Suchmaschine"),
+        ui.HTML("<hr>"),
+        ui.row(
+            ui.column(6, ui.input_text("search_input", "Suche", placeholder="Gib Suchterm ein", value="Leipzig", width="100%")),
+            ui.column(3,
+                      ui.input_select("sorting_method", "Sortierung", {"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"),
+                      style="display: flex; flex-direction: column; align-items: center; justify-content: center;"),
+            style="justify-content:space-between;"
+
+        ),
+        ui.output_ui(id="searchable_tweet_ui"),
+    )
+
+
+@ module.server
+def searchable_server(input: Inputs, output: Outputs, session: Session):
+    @ output
+    @ render.ui
+    def searchable_tweet_ui():
+
+        query = input.search_input()
+        sorting_method = input.sorting_method()
+        result_count = str(input.tweet_count())
+        if result_count == "all":
+            result_count = -1
+        else:
+            result_count = int(result_count)
+
+        result_pd, found_tweets = search_query(query, result_count, sorting_method=sorting_method)
+
+        style = "text-align: center;"
+        tweet_ui = ui.page_fluid(
+            ui.HTML(f"Gesamt gefundene Tweets: <b>{found_tweets}</b>"),
+            ui.HTML("<hr><br>"),
+        )
+
+        if result_pd is None:
+            return ui.div(
+                ui.h5("Keine Ergebnisse gefunden!")
+            )
+
+        # iterating over dataframe is bad but needed
+        for idx, row in result_pd.iterrows():
+
+            # prettify tweet text
+            tweet_text = str(row["tweet_text"]).replace("\\n", "<br>")
+            tweet_text = re.sub(link_regex, replace_link, tweet_text)
+            tweet_text = re.sub(hashtag_regex, replace_hastag, tweet_text)
+
+            tweet_link = f"https://twitter.com/{row['handle']}/status/{row['tweet_id']}"
+
+            user_handle = row['handle']
+            user_name = row['user_name']
+
+            tweet_ui.append(
+                ui.div(
+                    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']}"), style=style + "padding-top: 1.5em;"),
+                    ),
+                    ui.row(
+                        ui.column(12, ui.HTML("<hr>"),
+                                  ui.HTML(f"""
+                                    <style type="text/css">
+                                        .box {{
+                                            cursor: pointer;
+                                            text-align: center;
+                                            font-size: 20px;
+                                            padding-left: 1.5em;
+                                            padding-right: 1.5em;
+                                        }}
+                                        .box:hover {{
+                                            opacity: 0.7;
+                                            background: #eee;
+                                        }}
+                                    </style>
+                                    <div class="box"; onclick="location.href='{tweet_link}';">{tweet_text}</div></a>
+                                    """),
+                                  ui.HTML("<hr>")),
+                    ),
+                    ui.row(
+                        ui.column(3, ui.HTML(reply_html_svg), ui.p(
+                            f"{row['reply_count']}"), style=style, title="Antworten"),
+                        ui.column(3, ui.HTML(retweet_html_svg), ui.p(
+                            f"{row['retweet_count']}"), style=style, title="Retweets"),
+                        ui.column(3, ui.HTML(like_html_svg), ui.p(
+                            f"{row['like_count']}"), style=style, title="Likes"),
+                        ui.column(3, ui.HTML(quote_count_svg), ui.p(
+                            f"{row['quote_count']}"), style=style, title="Quotes"),
+                    ), style="border: 2px solid #119; margin-bottom: 1.5em; border-radius: 10px;"))
+
+        return tweet_ui

src/mod_welcome.py

@@ -18,7 +18,6 @@ def welcome_ui():
 
             [0]: https://ag-link.xyz
             """),
-        # ui.output_text("dataset_infos"),
         ui.output_ui("dataset_infos"),
         ui.h3("Ursprung der Idee"),
         ui.markdown("""
@@ -52,7 +51,7 @@ with open("data/general_analysis_results.json", "r") as f:
 
 
 @ module.server
-def welcome_server(input, output, session, starting_value=0):
+def welcome_server(input, output, session):
     @output
     @render.ui
     def dataset_infos():