Add scaling strategies

frontend/normstrategy.py

@@ -3,16 +3,20 @@ from pandas import DataFrame, Series
 from pandas.api.types import is_numeric_dtype
 from typing import Any, Union
 
-class MVStrategy(ABC):
-    """A way to handle missing values in a dataframe."""
+class DataFrameFunction(ABC):
+    """A command that may be applied in-place to a dataframe."""
 
     @abstractmethod
     def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
-        """Apply the current strategy to the given series.
+        """Apply the current function to the given dataframe, in-place.
 
         The series is described by its label and dataframe."""
         return df
 
+
+class MVStrategy(DataFrameFunction):
+    """A way to handle missing values in a dataframe."""
+
     @staticmethod
     def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
         """Get all the strategies that can be used."""
@@ -22,6 +26,20 @@ class MVStrategy(ABC):
         return choices
 
 
+class ScalingStrategy(DataFrameFunction):
+    """A way to handle missing values in a dataframe."""
+
+    @staticmethod
+    def list_available(df: DataFrame, series: Series) -> list['MVStrategy']:
+        """Get all the strategies that can be used."""
+        choices = [KeepStrategy()]
+        if is_numeric_dtype(series):
+            choices.extend((MinMaxStrategy(), ZScoreStrategy()))
+            if series.sum() != 0:
+                choices.append(UnitLengthStrategy())
+        return choices
+
+
 class DropStrategy(MVStrategy):
     #@typing.override
     def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
@@ -77,3 +95,44 @@ class LinearRegressionStrategy(MVStrategy):
 
     def __str__(self) -> str:
         return "Use linear regression"
+
+
+class KeepStrategy(ScalingStrategy):
+    #@typing.override
+    def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
+        return df
+
+    def __str__(self) -> str:
+        return "No-op"
+
+
+class MinMaxStrategy(ScalingStrategy):
+    #@typing.override
+    def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
+        minimum = series.min()
+        maximum = series.max()
+        df[label] = (series - minimum) / (maximum - minimum)
+        return df
+
+    def __str__(self) -> str:
+        return "Min-max"
+
+
+class ZScoreStrategy(ScalingStrategy):
+    #@typing.override
+    def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
+        df[label] = (series - series.mean()) / series.std()
+        return df
+
+    def __str__(self) -> str:
+        return "Z-Score"
+
+
+class UnitLengthStrategy(ScalingStrategy):
+    #@typing.override
+    def apply(self, df: DataFrame, label: str, series: Series) -> DataFrame:
+        df[label] = series / series.sum()
+        return df
+
+    def __str__(self) -> str:
+        return "Unit length"

frontend/pages/normalization.py

@@ -1,14 +1,15 @@
 import streamlit as st
-from mvstrategy import MVStrategy
+from normstrategy import MVStrategy, ScalingStrategy
 
 if "data" in st.session_state:
     data = st.session_state.data
     st.session_state.data = data.copy()
 
     for column, series in data.items():
+        col1, col2 = st.columns(2)
         missing_count = series.isna().sum()
         choices = MVStrategy.list_available(data, series)
-        option = st.selectbox(
+        option = col1.selectbox(
             f"Missing values of {column} ({missing_count})",
             choices,
             index=1,
@@ -17,6 +18,14 @@ if "data" in st.session_state:
         # Always re-get the series to avoid reusing an invalidated series pointer
         data = option.apply(data, column, data[column])
 
+        choices = ScalingStrategy.list_available(data, series)
+        option = col2.selectbox(
+            "Scaling",
+            choices,
+            key=f"scaling-{column}",
+        )
+        data = option.apply(data, column, data[column])
+
     st.write(data)
     st.session_state.working_data = data
 else: