UFCData 0.7.1__tar.gz → 0.7.3__tar.gz

{ufcdata-0.7.1 → ufcdata-0.7.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: UFCData
-Version: 0.7.1
+Version: 0.7.3
 Summary: Obtain UFC data and functions to manipulate it
 Requires-Python: >=3.10
 License-File: LICENSE.md

{ufcdata-0.7.1 → ufcdata-0.7.3}/README.md

@@ -295,7 +295,7 @@ data = ufc.get_data()
 
 fighter_bio = data["fighter_bio"].copy()
 fights_df = data["past_fights"].copy()
-rounds_df = data['past_rounds'].copy()
+rounds_df = data['rounds'].copy()
 future_df = data['future_fights']
 
 jon_jones = ufc.search(
@@ -322,16 +322,16 @@ jon_jones_current, jon_jones_past = ufc.get_fighter_statistic(
 The function `convert_odds()` converts American betting odds from strings into integers or floating point numbers.
 
 ```python
-convert_odds(odds, probability)
+convert_odds(odds)
 ```
 
 ### Parameters
 
-* `odds` — American betting odds as a string.
+* `odds` — American betting odds as a string, integer, float or None.
 
 ### Returns
 
-If probability=True, it returns a `float` representing the implied probability of the betting odds.
+Returns a `float` representing the implied probability of the betting odds.
 
 For positive American odds:
 
@@ -344,7 +344,6 @@ For negative American odds:
 ```text
 Probability = -odds / (-odds + 100)
 ```
-If probability=False, takes the string and converts it to an integer.
 
 ### Example
 
@@ -355,13 +354,8 @@ data = ufc.get_data()
 
 fights_df = data["past_fights"].copy()
 
-fights_df["Fighter 1 Odds"] = fights_df["Fighter 1 Odds"].apply(
-    ufc.convert_odds
-)
-
 fights_df["Fighter 1 Probability"] = fights_df["Fighter 1 Odds"].apply(
-    ufc.convert_odds,
-    probability=True
+    ufc.convert_odds
 )
 ```
 
@@ -650,12 +644,12 @@ past_fights = past_fights[past_fights[["Fighter 1 Odds", "Fighter 2 Odds"]].notn
 ## Convert odds to probabilities
 past_fights["Fighter 1 Probability"] = (
     past_fights["Fighter 1 Odds"]
-    .apply(ufc.convert_odds, probability=True)
+    .apply(ufc.convert_odds)
 )
 
 past_fights["Fighter 2 Probability"] = (
     past_fights["Fighter 2 Odds"]
-    .apply(ufc.convert_odds, probability=True)
+    .apply(ufc.convert_odds)
 )
 
 ## Create the data for cross validation and final testing
@@ -706,12 +700,12 @@ future_fights = data["future_fights"].copy()
 
 future_fights["Fighter 1 Probability"] = (
     future_fights["Fighter 1 Odds"]
-    .apply(ufc.convert_odds, probability=True)
+    .apply(ufc.convert_odds)
 )
 
 future_fights["Fighter 2 Probability"] = (
     future_fights["Fighter 2 Odds"]
-    .apply(ufc.convert_odds, probability=True)
+    .apply(ufc.convert_odds)
 )
 
 future_fights["Predicted Winner"] = np.where(

{ufcdata-0.7.1 → ufcdata-0.7.3}/UFCData.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: UFCData
-Version: 0.7.1
+Version: 0.7.3
 Summary: Obtain UFC data and functions to manipulate it
 Requires-Python: >=3.10
 License-File: LICENSE.md

ufcdata-0.7.3/pyproject.toml

@@ -0,0 +1,22 @@
+[build-system]
+requires = ["setuptools>=40.8.0", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "UFCData"
+version = "0.7.3"
+description = "Obtain UFC data and functions to manipulate it"
+requires-python = ">=3.10"
+
+dependencies = [
+    "huggingface-hub",
+    "pandas",
+    "numpy",
+    "glicko2",
+    "rapidfuzz",
+    "matplotlib",
+]
+
+[tool.setuptools.packages.find]
+include = ["ufcdata*"]
+exclude = ["scraper*", "UFCData_backup*"]

{ufcdata-0.7.1 → ufcdata-0.7.3}/ufcdata/fighter.py

@@ -694,4 +694,4 @@ def get_fighter_statistic(fighter_link, fighter_bio, fights_df, rounds_df,
     current_statistic["Date"] = np.nan
     past_statistic = statistic.iloc[1:].reset_index(drop=True)
 
-    return (current_statistic, past_statistic)
+    return (current_statistic, past_statistic)

{ufcdata-0.7.1 → ufcdata-0.7.3}/ufcdata/helper.py

@@ -2,9 +2,9 @@ import re
 import pandas as pd
 import numpy as np
 
-def convert_odds(odds, probability=False):
+def convert_odds(odds):
     """
-    Convert American betting odds to a numeric value or implied probability.
+    Convert American betting odds to implied probability.
 
     Parameters
     ----------
@@ -12,23 +12,16 @@ def convert_odds(odds, probability=False):
         American betting odds. The function extracts the first signed or
         unsigned integer from the input. Missing values return None.
 
-    probability : bool, default=False
-        If False, return the extracted American odds as an integer.
-        If True, return the implied probability as a decimal.
-
     Returns
     -------
-    int or float or None
-        The extracted American odds if probability=False, otherwise the
-        implied probability. Returns None for missing values.
+    float or None
+        The implied probability as a decimal. Returns None for missing values.
 
     Examples
     --------
     >>> convert_odds("+120")
-    120
+    0.45454545454545453
     >>> convert_odds("-400")
-    -400
-    >>> convert_odds("-400", probability=True)
     0.8
     """
     if pd.isna(odds):
@@ -36,9 +29,6 @@ def convert_odds(odds, probability=False):
 
     odds = int(re.search(r'[+-]?\d+', str(odds)).group())
 
-    if not probability:
-        return odds
-
     if odds < 0:
         return -odds / (-odds + 100)
     else:

{ufcdata-0.7.1 → ufcdata-0.7.3}/ufcdata/ratings.py

@@ -1,5 +1,4 @@
 import pandas as pd
-from glicko2 import Player
 
 #@title Elo function
 def expected_score(rating, opponent_rating, s):
@@ -11,7 +10,7 @@ def update_rating(rating, k, outcome, expected):
 
 # Elo function
 #  Make sure fights are sorted from most recent to least recent. Gets Elo prior to fight.
-def get_elo(fight_df, fighter_df, r=1500, k=30, s=400):
+def get_elo(r=1500, k=30, s=400):
   """
     Calculates pre-fight Elo ratings for UFC fighters.
 
@@ -22,13 +21,6 @@ def get_elo(fight_df, fighter_df, r=1500, k=30, s=400):
 
     Parameters
     ----------
-    fight_df : pandas.DataFrame
-        UFC fight data sorted from most recent to least recent.
-        Must contain fighter links, fight outcomes, and the fight
-        information required to construct the output.
-    fighter_df : pandas.DataFrame
-        DataFrame containing fighter information. Must contain a
-        "Fighter Link" column used to identify each fighter.
     r : float, default=1500
         Initial Elo rating assigned to each fighter.
     k : float, default=30
@@ -47,20 +39,25 @@ def get_elo(fight_df, fighter_df, r=1500, k=30, s=400):
         Fight-level DataFrame containing the original fight information
         and the Elo rating of each fighter immediately before the fight.
 
-    Notes
-    -----
-    The input fight data should be sorted from most recent to least
-    recent. The function reverses this order internally to process
-    fights chronologically, then returns the resulting data in the
-    original order.
-
     Examples
     --------
-    >>> fighter_elo, fight_elo = get_elo(fight_df, fighter_df)
+    >>> fighter_elo, fight_elo = get_elo(1000, 10, 20)
     >>> fight_elo[["Fighter 1", "Fighter 1 Elo",
     ...            "Fighter 2", "Fighter 2 Elo"]].head()
   """
 
+
+  past_fights = (
+      f"https://huggingface.co/datasets/JunoML/MMA/resolve/main/"
+      f"past_fights.csv"
+  )
+
+  fighter_bio = (
+      f"https://huggingface.co/datasets/JunoML/MMA/resolve/main/"
+      f"fighter_bio.csv"
+  )
+  
+  fight_df = pd.read_csv(past_fights)
   fight_df = fight_df[::-1]
 
   original_fight_df = fight_df.copy()
@@ -69,12 +66,14 @@ def get_elo(fight_df, fighter_df, r=1500, k=30, s=400):
   fighter_2_elo = []
 
   ## Create a dictionary of fighters and their Elo
+  fighter_df = pd.read_csv(fighter_bio)
   fighter_df = fighter_df.copy()
   fighter_df["Elo"] = r
   fighter_df = dict(zip(fighter_df["Fighter Link"], fighter_df["Elo"]))
 
   ## Create a list of fights
-  fight_df = fight_df[["Fighter 1 Link", "Fighter 1 Outcome", "Fighter 2 Link", "Fighter 2 Outcome"]]
+  fight_df = fight_df[["Fighter 1 Link", "Fighter 1 Outcome", 
+                       "Fighter 2 Link", "Fighter 2 Outcome"]]
   fight_df = fight_df.values.tolist()
 
 
@@ -120,11 +119,15 @@ def get_elo(fight_df, fighter_df, r=1500, k=30, s=400):
     ],
     axis=1
   )
-  elo = elo[['Date', 'Event Link', 'Fight Number', 'Fight Link', 'Weight Class',
-       'Gender', 'Title', 'Fighter 1', 'Fighter 1 Elo', 'Fighter 1 Odds', 'Fighter 1 Link',
-       'Fighter 1 Outcome', 'Fighter 1 Bonus', 'Fighter 2','Fighter 2 Elo', 'Fighter 2 Odds',
-       'Fighter 2 Link', 'Fighter 2 Outcome', 'Fighter 2 Bonus', 'Method',
-       'Round', 'Time', 'Time Format', 'Referee', 'Details']]
+  elo = elo[['Date', 'Event Link', 'Fight Number',
+             'Fight Link', 'Weight Class', 'Gender', 
+             'Title', 'Fighter 1', 'Fighter 1 Elo', 
+             'Fighter 1 Odds', 'Fighter 1 Link',
+             'Fighter 1 Outcome', 'Fighter 1 Bonus', 
+             'Fighter 2','Fighter 2 Elo', 'Fighter 2 Odds',
+             'Fighter 2 Link', 'Fighter 2 Outcome',
+             'Fighter 2 Bonus', 'Method', 'Round', 'Time',
+             'Time Format', 'Referee', 'Details']]
   past_elo = elo[::-1].copy()
   current_elo = fighter_df
-  return (current_elo, past_elo)
+  return (current_elo, past_elo)

ufcdata-0.7.3/ufcdata/search.py

@@ -0,0 +1,46 @@
+from rapidfuzz.fuzz import ratio
+import pandas as pd
+
+def search(data, column , query, matches=1):
+    """
+    Searches a UFC dataset for rows matching a query.
+
+    The dataset is loaded as a CSV file from the JunoML/MMA Hugging Face
+    repository. Fuzzy string matching is used to identify the rows in the
+    specified column that most closely match the query.
+
+    Parameters
+    ----------
+    data : str
+        Name of the CSV dataset to search, without the .csv extension.
+        For example, "fighter_bio".
+    column : str
+        Name of the column to search.
+    query : str
+        Search query to match against the specified column.
+    matches : int, default=1
+        Number of closest matches to return.
+
+    Returns
+    -------
+    pandas.DataFrame
+        DataFrame containing the closest matching rows, sorted from
+        highest to lowest similarity. The index is reset.
+
+    Examples
+    --------
+    >>> results = search("fighter_bio", "Name", "John Jones", 1)
+    >>> print(results)
+    """
+
+    url = f"https://huggingface.co/datasets/JunoML/MMA/resolve/main/{data}.csv"
+    df = pd.read_csv(url)
+
+    scores = df[column].fillna("").apply(
+    lambda x: ratio(str(x), query))
+
+    result = df.loc[scores.nlargest(matches).index].copy()
+    result["score"] = scores.loc[result.index]
+    result = result.sort_values("score", ascending=False).drop(columns="score")
+
+    return result.reset_index(drop=True)

ufcdata-0.7.1/pyproject.toml

@@ -1,14 +0,0 @@
-[project]
-name = "UFCData"
-version = "0.7.1"
-description = "Obtain UFC data and functions to manipulate it"
-requires-python = ">=3.10"
-
-dependencies = [
-    "huggingface-hub",
-    "pandas",
-    "numpy",
-    "glicko2",
-    "rapidfuzz",
-    "matplotlib",
-]

ufcdata-0.7.1/ufcdata/search.py

@@ -1,39 +0,0 @@
-from rapidfuzz.fuzz import ratio
-
-def search(data, column , query, matches=1):
-    """
-    Searches a UFC DataFrame for rows matching a query.
-
-    Uses fuzzy string matching to identify the rows in the specified
-    column that most closely match the query.
-
-    Parameters
-    ----------
-    data : pandas.DataFrame
-        UFC DataFrame to search.
-    column : str
-        Name of the column to search.
-    query : str
-        Search query to match against the specified column.
-    matches : int, default=1
-        Number of closest matches to return.
-
-    Returns
-    -------
-    pandas.DataFrame
-        DataFrame containing the closest matching rows, sorted from
-        highest to lowest similarity.
-
-    Examples
-    --------
-    >>> data = get_data()
-    >>> results = search(data["fighters"], "Name", "Jon Jones")
-    """
-    scores = data[column].fillna("").apply(
-    lambda x: ratio(str(x), query))
-
-    result = data.loc[scores.nlargest(matches).index].copy()
-    result["score"] = scores.loc[result.index]
-    result = result.sort_values("score", ascending=False).drop(columns="score")
-
-    return result