Squashed 'utils_v2/' content from commit aa76ceb

git-subtree-dir: utils_v2 git-subtree-split: aa76ceb7480020f473af5cdb44891d3ebcfc8373
2024-12-05 10:29:29 +05:30
commit 24f5bc60dc
143 changed files with 125300 additions and 0 deletions
@@ -0,0 +1,168 @@
+"""
+
+    AUTHOR:
+
+        Khushal P Soonderji
+
+    DATE:
+
+        Saturday, 18th May, 2024
+
+    OBJECTIVE:
+
+        To provide a quick set of functions to work with fuzzy logic.
+
+    REFERENCES:
+
+        1) https://www.w3schools.com/python/python_json.asp
+
+    DOWNLOADS:
+
+        N/A
+
+"""
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                                   IMPORT                                                      ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+# To make sibling directories accessible for imports:
+import sys
+sys.path.append(".")
+sys.path.append("..")
+
+# To apply fuzzy logic:
+from thefuzz import fuzz, process
+
+# To work with tabulated data:
+import pandas as pd
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                           MACROS / ONE-TIME INIT                                              ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+# --- Nothing Yet
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                                VARIABLES                                                      ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+# --- Nothing Yet
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                                  FUNCTIONS                                                    ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+def get_best_match(
+        target,
+        choices,
+        threshold = 0.70,
+        partial = False
+):
+
+    if partial: scorer = fuzz.partial_token_sort_ratio
+    else: scorer = fuzz.ratio
+
+    result = process.extractOne(
+        target,
+        choices,
+        score_cutoff = threshold * 100,
+        scorer = scorer
+    )
+
+    try: return result[0]
+    except: return None
+
+
+# ---------------------------------------------------------------------------------------------------------------------
+
+
+def rank(target, choices, partial = True):
+
+    if partial: scorer = fuzz.partial_token_sort_ratio
+    else: scorer = fuzz.ratio
+
+    result = process.extract(
+        target,
+        choices,
+        limit = len(choices),
+        scorer = scorer
+    )
+
+    result = pd.DataFrame(result, columns = ["choice", "closeness"])
+    result["closeness"] = result["closeness"] / 100.0
+
+    return result
+
+
+# ---------------------------------------------------------------------------------------------------------------------
+
+
+def match(targets, choices, threshold = 0.7, partial = False, allow_null = False):
+
+    all_matches_df = None
+    all_matches = {target: None for target in targets}
+    something_is_null = False
+
+    for target in targets:
+        match_df = rank(target, choices, partial = partial)
+        match_df["target"] = target
+        if all_matches_df is None: all_matches_df = match_df
+        else: all_matches_df = pd.concat([all_matches_df, match_df])
+
+    all_matches_df = all_matches_df.sort_values(by = ["closeness"], ascending = False).reset_index(drop = True)
+
+    for target in targets:
+        target_df = all_matches_df[all_matches_df["target"] == target].reset_index(drop = True)
+        if target_df.empty: continue
+        if target_df.at[0, "closeness"] >= threshold:
+            choice = target_df.at[0, "choice"]
+            all_matches[target] = choice
+            all_matches_df = all_matches_df[all_matches_df["choice"] != choice]
+        else:
+            all_matches[target] = None
+            something_is_null = True
+
+    # print(all_matches)
+    if something_is_null and not allow_null: return None
+    else: return all_matches
+
+
+#   *****************************************************************************************************************
+#  *****                                                                                                          ****
+# ***                                               MAIN PROGRAM                                                    ***
+#  *****                                                                                                          ****
+#   *****************************************************************************************************************
+
+
+if __name__ == "__main__":
+
+    import async_json_utils
+
+    awb_numbers = [
+        "SF1111BIC",
+        "SF2222BIC",
+        "SF3333BIC",
+        "SF4444BIC",
+    ]
+
+    chat_text = "SF1112BIC"
+
+    # print(chat_text == names[0])
+    best_match = get_best_match(chat_text, awb_numbers, threshold = 0.60, partial = False)
+    print(f"Best match for '{chat_text}' is '{best_match}'")