Merge branch 'master' of...

Merge branch 'master' of ssh://gitup.uni-potsdam.de/nifranz/rse-23-group-assignment-shervud-pitawanik-franz

docs/class_diagram.drawio

+<mxfile host="Electron" modified="2023-07-12T16:27:44.192Z" agent="5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/15.8.7 Chrome/91.0.4472.164 Electron/13.6.2 Safari/537.36" etag="cKdbLBWRQm2rR1pnQ_-2" version="15.8.7" type="device"><diagram id="C5RBs43oDa-KdzZeNtuy" name="Page-1">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</diagram></mxfile>
\ No newline at end of file

src/Dataset.py

@@ -122,7 +122,7 @@ class Dataset:
         is_competitive_col = self.get_is_competitive_col(dataframe)
         return is_competitive_col
 
-    def treat_outliers(self, df, colname):
+    def treat_outliers(self, df, colname) -> pd.DataFrame:
         q = df[colname].quantile(0.99)
         return df[df[colname] < q]
 

src/Plotter.py

@@ -10,13 +10,35 @@ class Plotter:
         self.ds = dataset
         self.df = dataset.get_dataframe()
 
-    def customize_plot(self, fig, ax, styling_params):
+    def customize_plot(self, fig, ax, styling_params) -> None:
+        """ customize_plot
+
+        Args:
+            fig (plt.figure.Figure),
+            ax (plt.axes.Axes),
+            styling_params (dict)
+
+
+        Returns:
+            None
+        """
         if styling_params.get("title"):
             ax.set_title(styling_params["title"])
 
     def plot_categorical_bar_chart(
         self, category1, category2, styling_params={}
-    ):
+    ) -> None:
+        """ plot a categorical bar chart.
+
+        Args:
+            category1 (str, must be present as a column in the dataset),
+            category2 (str, must be present as a column in the dataset),
+            styling_params (dict)
+
+
+        Returns:
+            None
+        """
         ct = pd.crosstab(self.df[category1], self.df[category2])
         # Calculate percentages by row
         ct_percent = ct.apply(lambda r: r / r.sum() * 100, axis=0)
@@ -24,14 +46,39 @@ class Plotter:
         self.customize_plot(fig, ax, styling_params)
         ct_percent.plot(kind="bar", ax=ax)
 
-    def plot_categorical_boxplot(self, target, category, styling_params={}):
+    def plot_categorical_boxplot(
+        self, target, category, styling_params={}
+    ) -> None:
+        """ plot a categorical boxplot.
+
+        Args:
+            target (str, must be present as a column in the dataset),
+            category (str, must be present as a column in the dataset),
+            styling_params (dict)
+
+
+        Returns:
+            None
+        """
+        
         fig, ax = plt.subplots()
         self.customize_plot(fig, ax, styling_params)
         sns.boxplot(x=category, y=target, data=self.df, palette="rainbow")
 
     def plot_categorical_histplot(
         self, target, category, styling_params={}, bins=30
-    ):
+    ) -> None:
+        """ plot a categorical hisplot.
+
+        Args:
+            target (str, must be present as a column in the dataset),
+            category (str, must be present as a column in the dataset),
+            styling_params (dict)
+
+
+        Returns:
+            None
+        """
         uniques = self.ds.get_unique_column_values(category)
         fig, ax = plt.subplots()
         self.customize_plot(fig, ax, styling_params)
@@ -45,20 +92,29 @@ class Plotter:
                 alpha=0.5,
             )
 
-    def plot_scatterplot(self, target1, target2, styling_params={}):
+    def plot_scatterplot(self, target1, target2, styling_params={}) -> None:
+        """ plot a scatterplot.
+
+        Args:
+            target1 (str, must be present as a column in the dataset),
+            target2 (str, must be present as a column in the dataset),
+            styling_params (dict)
+
+
+        Returns:
+            None
+        """
         fig, ax = plt.subplots()
         self.customize_plot(fig, ax, styling_params)
         ax.scatter(self.df[target1], self.df[target2])
-
-    def distribution_plot(self, target):
-        fig, ax = plt.subplots()
+   def distribution_plot(self, target):
         grouped_data = self.df.groupby(target).size()
-        ax.barh(grouped_data.index, grouped_data.values)
+        plt.barh(grouped_data.index, grouped_data.values)
         print(
             str(grouped_data),
             str(grouped_data.index),
             str(grouped_data.values),
         )
-        ax.set_xlabel("Size")
-        ax.set_ylabel(target)
-        ax.set_title(f"Distribution of {target}")
+        plt.xlabel("Size")
+        plt.ylabel(target)
+        plt.title(f"Distribution of {target}")
\ No newline at end of file