From ac0c2a8c211756356f07e60969adbab632328cb7 Mon Sep 17 00:00:00 2001
From: Peter Vacho <p_vacho@utb.cz>
Date: Mon, 25 Nov 2024 11:50:06 +0100
Subject: [PATCH] Store ranking into the cache

---
 src/__main__.py | 16 ++++++++++++++--
 src/util.py     | 32 ++++++++++++++++++++++++++++++++
 2 files changed, 46 insertions(+), 2 deletions(-)

diff --git a/src/__main__.py b/src/__main__.py
index f9283aa..9489590 100644
--- a/src/__main__.py
+++ b/src/__main__.py
@@ -9,7 +9,7 @@ import pandas as pd
 
 from src.link_scraper import get_urlmap, standard_urlmap_exception_suppressor
 from src.pagerank import pagerank, test_pagerank
-from src.util import dataframe_to_urlmap, urlmap_to_dataframe
+from src.util import add_ratings_to_dataframe, dataframe_to_urlmap, extract_ratings_from_dataframe, urlmap_to_dataframe
 from src.visualization import display_top_urls
 
 URL = httpx.URL("https://ailab.fai.utb.cz")
@@ -60,10 +60,22 @@ async def main() -> None:
     print("Ranking...")
     start = perf_counter()
 
-    ranking = pagerank(url_map)
+    if "rating" in url_map_df:
+        print("> Rankings recovered from cache")
+        ranking = extract_ratings_from_dataframe(url_map_df)
+    else:
+        print("> Cache doesn't contain rankings, computing")
+        del url_map_df
+        ranking = pagerank(url_map)
+
+        print("> Storing rankings into the cache")
+        url_map_df = urlmap_to_dataframe(url_map)
+        add_ratings_to_dataframe(url_map_df, ranking)
+        url_map_df.to_csv(cache_file)
 
     took = perf_counter() - start
     print(f"Took: {round(took, 2)} seconds")
+
     print("Done")
 
     display_top_urls(ranking)
diff --git a/src/util.py b/src/util.py
index 4fe77b7..b6453a6 100644
--- a/src/util.py
+++ b/src/util.py
@@ -26,3 +26,35 @@ def dataframe_to_urlmap(df: pd.DataFrame) -> dict[httpx.URL, set[httpx.URL]]:
             urlmap[source_url] = set()
         urlmap[source_url].add(target_url)
     return urlmap
+
+
+def add_ratings_to_dataframe(df: pd.DataFrame, ratings: dict[httpx.URL, float]) -> None:
+    """Add ratings to the DataFrame (mutating it).
+
+    :param df: The DataFrame containing 'source' and 'target' columns.
+    :param ratings: A dictionary mapping each URL to its PageRank rating.
+    """
+    # Add a new column 'rating' based on the 'source' column
+    if "source" in df:
+        df["rating"] = df["source"].apply(lambda x: ratings.get(httpx.URL(x), None))
+        return
+
+    # empty dataframe
+    if len(ratings) == 0:
+        return
+
+    raise ValueError("Got an empty dataframe with non-empty ratings dict")
+
+
+def extract_ratings_from_dataframe(df: pd.DataFrame) -> dict[httpx.URL, float]:
+    """Extract ratings from a DataFrame and update the original ratings dictionary.
+
+    :param df: DataFrame containing 'source' and 'rating' columns.
+    :return: A dictionary where the key is the URL and the value is the rating.
+    """
+    ratings = {}
+    for _, row in df.iterrows():
+        url = httpx.URL(row["source"])  # Extract the source URL
+        rating = row["rating"]  # Extract the rating
+        ratings[url] = rating  # Add it to the dictionary
+    return ratings