upload test summary file

README.md

@@ -30,7 +30,7 @@ Interested in contributing? Check out the contributing guidelines. Please note t
 
 ## License
 
-`dataprofiler` was created by DongchunChen, Ismail (Husain) Bhinderwala and Jingyuan Wang. It is licensed under the terms of the MIT license.
+`dataprofiler` was created by Dongchun Chen, Ismail (Husain) Bhinderwala and Jingyuan Wang. It is licensed under the terms of the MIT license.
 
 ## Credits
 

src/dataprofiler/dataprofiler.py

@@ -20,11 +20,41 @@ def summarize_data(df):
         A DataFrame where each row corresponds to a numeric column in the input DataFrame,
         and the columns represent the calculated statistics: min, 25%, 50% (median), 75%, and max.
 
+	Raises
+    ------
+    TypeError
+        If the input is not a pandas DataFrame.
+    ValueError
+        If the DataFrame is empty or contains no numeric columns.
+
     Example
     -------
     >>> summarize_data(df)
     """
-    pass
+
+	# Check if input is a DataFrame
+    if not isinstance(df, pd.DataFrame):
+        raise TypeError("Input must be a pandas DataFrame.")
+
+    # Check if DataFrame is empty
+    if df.empty:
+        raise ValueError("The input DataFrame is empty.")
+
+    # Select numeric columns
+    numeric_cols = df.select_dtypes(include=['number'])
+
+    # Check if there are numeric columns
+    if numeric_cols.empty:
+        raise ValueError("The DataFrame contains no numeric columns.")
+
+    # Calculate summary statistics
+    summary = numeric_cols.describe(percentiles=[0.25, 0.5, 0.75]).T
+
+    # Select relevant statistics
+    summary = summary[['min', '25%', '50%', '75%', 'max']]
+
+    return summary
+
 
 def detect_anomalies(df):
     """Detect anomalies in a dataframe, including missing values, outliers, and duplicates.

tests/test_summarize_data.py

@@ -0,0 +1,47 @@
+import pytest
+import pandas as pd
+from dataprofiler.dataprofiler import summarize_data
+
+def test_summarize_data_normal():
+    """Test summarize_data with a normal DataFrame containing numeric columns."""
+    data = {
+        'A': [1, 2, 3, 4, 5],
+        'B': [10, 20, 30, 40, 50]
+    }
+    df = pd.DataFrame(data)
+    result = summarize_data(df)
+    expected_columns = ['min', '25%', '50%', '75%', 'max']
+    assert all(col in result.columns for col in expected_columns)
+    assert result.shape[0] == 2  # Two numeric columns
+
+def test_summarize_data_single_column():
+    """Test summarize_data with a DataFrame containing a single numeric column."""
+    data = {'A': [1, 2, 3, 4, 5]}
+    df = pd.DataFrame(data)
+    result = summarize_data(df)
+    assert result.shape == (1, 5)
+    assert result.loc['A', 'min'] == 1
+    assert result.loc['A', 'max'] == 5
+
+def test_summarize_data_empty_dataframe():
+    """Test summarize_data with an empty DataFrame."""
+    df = pd.DataFrame()
+    with pytest.raises(ValueError, match="The input DataFrame is empty."):
+        summarize_data(df)
+
+def test_summarize_data_no_numeric_columns():
+    """Test summarize_data with a DataFrame containing no numeric columns."""
+    data = {
+        'A': ['x', 'y', 'z'],
+        'B': ['foo', 'bar', 'baz']
+    }
+    df = pd.DataFrame(data)
+    with pytest.raises(ValueError, match="The DataFrame contains no numeric columns."):
+        summarize_data(df)
+
+def test_summarize_data_invalid_input():
+    """Test summarize_data with invalid input types."""
+    with pytest.raises(TypeError, match="Input must be a pandas DataFrame."):
+        summarize_data([1, 2, 3])  # Invalid input: list
+    with pytest.raises(TypeError, match="Input must be a pandas DataFrame."):
+        summarize_data("not a dataframe")  # Invalid input: string