From fe96d9471fd591c164b107625cd585117ec2e8c8 Mon Sep 17 00:00:00 2001
From: jessiezhang24 <zhangj24@student.ubc.ca>
Date: Thu, 9 Jan 2025 15:38:21 -0800
Subject: [PATCH] update README and add summary stats func

---
 README.md                 |  1 +
 src/pyeda/data_summary.py | 21 +++++++++++++++++++++
 2 files changed, 22 insertions(+)
 create mode 100644 src/pyeda/data_summary.py

diff --git a/README.md b/README.md
index 45bd770..a02ddfd 100644
--- a/README.md
+++ b/README.md
@@ -13,6 +13,7 @@ Catherine Meng, Jessie Zhang, Zheng He
 -   **`missing_value_summary`**\
     This function is to provide a summary of missing values in the dataset.
 -   **`get_summary_statistics`**
+    Generate summary statistics for specified columns or all columns if none are provided.
 
 ## Installation
 
diff --git a/src/pyeda/data_summary.py b/src/pyeda/data_summary.py
new file mode 100644
index 0000000..2ce0c98
--- /dev/null
+++ b/src/pyeda/data_summary.py
@@ -0,0 +1,21 @@
+def get_summary_statistics(df, col = None):
+    """
+    Generate summary statistics for specified columns or all columns if none are provided.
+
+    This function will return the important statistics (e.g. mean, min, std) for numeric columns, as well as
+    some key metrics (e.g. count, unique) for non-numeric columns.
+    
+    Parameters
+    ----------
+    df : pd.DataFrame
+        The dataframe containing the data for analysis.
+    col : list or None
+        A list of column names for which to get statistics. 
+        Default value is None, the function will apply for all columns.
+
+    Returns
+    ----------
+    pd.DataFrame
+        A DataFrame with summary statistics for the specified columns.
+    """
+    pass
\ No newline at end of file