Merge pull request #18 from UBC-MDS/checknullvalue

update from df to series

src/pyeda/pymissing_values_summary.py

@@ -3,15 +3,15 @@
 
 def missing_values_summary(df):
     """
-    This function is to provide a summary of missing values in the dataset.
+    This function is to provide a summary of missing values in the dataset as a Series.
 
     Parameters
     ----------
     df (pd.DataFrame): The DataFrame containing the data.
 
     Returns
     -------
-    pd.DataFrame: A DataFrame showing the count and percentage of missing values.
+    pd.Series: A Series showing the count and percentage of missing values.
 
     Examples
     --------
@@ -23,17 +23,10 @@ def missing_values_summary(df):
     # Calculate the percentage of missing values for each column
     missing_percentage = (missing_count / len(df)) * 100
 
-    # Create a summary DataFrame
-    missing_summary = pd.DataFrame({
-        'Missing Count': missing_count,
-        'Missing Percentage': missing_percentage
-    })
+    # Combine count and percentage into a Series, filtering out columns with no missing values
+    missing_summary = missing_count[missing_count > 0].astype(str) + " (" + \
+                      missing_percentage[missing_count > 0].round(2).astype(str) + "%)"
 
-    # Filter out columns with no missing values
-    missing_summary = missing_summary[missing_summary['Missing Count'] > 0]
-
-    # Sort the DataFrame by the count of missing values in descending order
-    missing_summary = missing_summary.sort_values(by='Missing Count', ascending=False)
-
-    return missing_summary
+    missing_summary.name = "Missing Count (Percentage)"
+    return missing_summary.sort_values(ascending=False) 
 

tests/test_missing.py

@@ -1,5 +1,4 @@
 from pyeda.pymissing_values_summary import missing_values_summary
-
 import pytest
 import pandas as pd
 
@@ -16,23 +15,21 @@ def df():
     return pd.DataFrame(data)
 
 
-
 def test_missing_values_summary(df):
     """
     Test for the missing_values_summary function.
     """
     result = missing_values_summary(df)
 
     # Expected results
-    expected_columns = ['Missing Count', 'Missing Percentage']
     expected_index = ['B', 'A']  # Columns with missing values in descending order of missing count
+    expected_values = ['2 (50.0%)', '1 (25.0%)']  # Expected values in the Series
+
+    # Check if the result is a Series
+    assert isinstance(result, pd.Series), "Result should be a Series."
 
-    # Check if the resulting DataFrame has the correct structure
-    assert list(result.columns) == expected_columns
-    assert list(result.index) == expected_index
+    # Check if the resulting Series has the correct index
+    assert list(result.index) == expected_index, "Index does not match the expected order."
 
-    # Check the specific values
-    assert result.loc['B', 'Missing Count'] == 2
-    assert result.loc['B', 'Missing Percentage'] == 50.0
-    assert result.loc['A', 'Missing Count'] == 1
-    assert result.loc['A', 'Missing Percentage'] == 25.0
+    # Check the specific values in the Series
+    assert list(result.values) == expected_values, "Values in the Series do not match the expected output."