From 8ae2953f7fd2a3b6312d0b66f0cd46e93a539e8d Mon Sep 17 00:00:00 2001
From: Alejandro Aristizabal <alejandro.aristizabal24@gmail.com>
Date: Tue, 12 Sep 2023 15:22:26 -0500
Subject: [PATCH] Implement empty statistics task

---
 .../data_preparation/project/statistics.py    | 44 +------------------
 1 file changed, 2 insertions(+), 42 deletions(-)

diff --git a/mlcubes/data_preparation/project/statistics.py b/mlcubes/data_preparation/project/statistics.py
index 31622c9e..04c7e0f6 100644
--- a/mlcubes/data_preparation/project/statistics.py
+++ b/mlcubes/data_preparation/project/statistics.py
@@ -4,44 +4,6 @@
 import pandas as pd
 
 
-def get_statistics(data_df: pd.DataFrame) -> dict:
-    """Computes statistics about the data. This statistics are uploaded
-    to the Medperf platform under the data owner's approval. Include
-    every statistic you consider useful for determining the nature of the
-    data, but keep in mind that we want to keep the data as private as
-    possible.
-
-    Args:
-        data_df (pd.DataFrame): DataFrame containing the prepared dataset
-
-    Returns:
-        dict: dictionary with all the computed statistics
-    """
-    stats = {
-        "weight": {
-            "mean": float(data_df["weight"].mean()),
-            "std": float(data_df["weight"].std()),
-            "min": float(data_df["weight"].min()),
-            "max": float(data_df["weight"].max()),
-        },
-        "volume": {
-            "mean": float(data_df["volume"].mean()),
-            "std": float(data_df["volume"].std()),
-            "min": float(data_df["volume"].min()),
-            "max": float(data_df["volume"].max()),
-        },
-        "density": {
-            "mean": float(data_df["density"].mean()),
-            "std": float(data_df["density"].std()),
-            "min": float(data_df["density"].min()),
-            "max": float(data_df["density"].max()),
-        },
-        "size": len(data_df),
-    }
-
-    return stats
-
-
 if __name__ == "__main__":
     parser = argparse.ArgumentParser("MedPerf Statistics Example")
     parser.add_argument(
@@ -60,10 +22,8 @@ def get_statistics(data_df: pd.DataFrame) -> dict:
 
     args = parser.parse_args()
 
-    namesfile = os.path.join(args.data, "data.csv")
-    names_df = pd.read_csv(namesfile)
-
-    stats = get_statistics(names_df)
+    # TODO: implement statistics
+    stats = {}
 
     with open(args.out_file, "w") as f:
         yaml.dump(stats, f)