Mise à jour de 'frontend/pages/clustering_dbscan.py'

frontend/normstrategy.py

@@ -1,7 +1,6 @@
 from abc import ABC, abstractmethod
 from pandas import DataFrame, Series
 from pandas.api.types import is_numeric_dtype
-from sklearn.neighbors import KNeighborsClassifier
 from typing import Any, Union
 
 class DataFrameFunction(ABC):
@@ -19,14 +18,11 @@ class MVStrategy(DataFrameFunction):
     """A way to handle missing values in a dataframe."""
 
     @staticmethod
-    def list_available(df: DataFrame, label: str, series: Series) -> list['MVStrategy']:
+    def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
         """Get all the strategies that can be used."""
         choices = [DropStrategy(), ModeStrategy()]
         if is_numeric_dtype(series):
             choices.extend((MeanStrategy(), MedianStrategy(), LinearRegressionStrategy()))
-            other_columns = df.select_dtypes(include="number").drop(label, axis=1).columns.to_list()
-            if len(other_columns):
-                choices.append(KNNStrategy(other_columns))
         return choices
 
 
@@ -101,43 +97,6 @@ class LinearRegressionStrategy(MVStrategy):
         return "Use linear regression"
 
 
-class KNNStrategy(MVStrategy):
-    def __init__(self, training_features: list[str]):
-        self.available_features = training_features
-        self.training_features = training_features
-        self.n_neighbors = 3
-
-    def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
-        # Remove any training column that have any missing values
-        usable_data = df.dropna(subset=self.training_features)
-        # Select columns to impute from
-        train_data = usable_data.dropna(subset=label)
-        # Create train dataframe
-        x_train = train_data.drop(label, axis=1)
-        y_train = train_data[label]
-
-        reg = KNeighborsClassifier(self.n_neighbors).fit(x_train, y_train)
-
-        # Create test dataframe
-        test_data = usable_data[usable_data[label].isnull()]
-        if test_data.empty:
-            return df
-        x_test = test_data.drop(label, axis=1)
-        predicted = reg.predict(x_test)
-
-        # Fill with predicated values and patch the original data
-        usable_data[label].fillna(Series(predicted), inplace=True)
-        df.fillna(usable_data, inplace=True)
-        return df
-
-    def count_max(self, df: DataFrame, label: str) -> int:
-        usable_data = df.dropna(subset=self.training_features)
-        return usable_data[label].count()
-
-    def __str__(self) -> str:
-        return "kNN"
-
-
 class KeepStrategy(ScalingStrategy):
     #@typing.override
     def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:

frontend/pages/normalization.py

@@ -1,5 +1,5 @@
 import streamlit as st
-from normstrategy import MVStrategy, ScalingStrategy, KNNStrategy
+from normstrategy import MVStrategy, ScalingStrategy
 
 if "data" in st.session_state:
     data = st.session_state.original_data
@@ -8,16 +8,13 @@ if "data" in st.session_state:
     for column, series in data.items():
         col1, col2 = st.columns(2)
         missing_count = series.isna().sum()
-        choices = MVStrategy.list_available(data, column, series)
+        choices = MVStrategy.list_available(data, series)
         option = col1.selectbox(
             f"Missing values of {column} ({missing_count})",
             choices,
             index=1,
             key=f"mv-{column}",
         )
-        if isinstance(option, KNNStrategy):
-            option.training_features = st.multiselect("Training columns", option.training_features, default=option.available_features, key=f"cols-{column}")
-            option.n_neighbors = st.number_input("Number of neighbors", min_value=1, max_value=option.count_max(data, column), value=option.n_neighbors, key=f"neighbors-{column}")
         # Always re-get the series to avoid reusing an invalidated series pointer
         data = option.apply(data, column, data[column])