numerai-tools 0.5.0.dev5__tar.gz → 0.5.0.dev6__tar.gz

{numerai_tools-0.5.0.dev5 → numerai_tools-0.5.0.dev6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.3
 Name: numerai-tools
-Version: 0.5.0.dev5
+Version: 0.5.0.dev6
 Summary: A collection of open-source tools to help interact with Numerai, model data, and automate submissions.
 License: MIT
 Author: Numerai Engineering

{numerai_tools-0.5.0.dev5 → numerai_tools-0.5.0.dev6}/numerai_tools/signals.py

@@ -66,9 +66,6 @@ def turnover(
     Arguments:
         s1: pd.Series - the first series to compare
         s2: pd.Series - the second series to compare
-        top_bottom: Optional[int] - the number of top and bottom predictions to use
-                                    when calculating the correlation. Results in
-                                    2*top_bottom predictions.
 
     Returns:
         float - the turnover between the two series
@@ -126,7 +123,10 @@ def calculate_max_churn_and_turnover(
     churn_stats = []
     turnover_stats = []
     neutralized_weights = generate_neutralized_weights(
-        curr_sub_vector.to_frame(), curr_neutralizer, curr_weight
+        curr_sub_vector.to_frame(),
+        curr_neutralizer,
+        curr_weight,
+        center_and_normalize=True,
     )
     for datestamp in prev_week_subs:
         prev_sub = prev_week_subs[datestamp]
@@ -167,7 +167,10 @@ def calculate_max_churn_and_turnover(
             curr_ticker_col,
         ).set_index(curr_ticker_col)[prev_weight.name]
         prev_neutralized_weights = generate_neutralized_weights(
-            filtered_prev_sub.to_frame(), prev_neutralizer, prev_weight
+            filtered_prev_sub.to_frame(),
+            prev_neutralizer,
+            prev_weight,
+            center_and_normalize=True,
         )
         try:
             churn_val = abs(churn(curr_sub_vector, filtered_prev_sub))

{numerai_tools-0.5.0.dev5 → numerai_tools-0.5.0.dev6}/numerai_tools/submissions.py

@@ -31,7 +31,6 @@ def _validate_headers(
     submission: pd.DataFrame,
     expected_id_cols: List[str],
     expected_pred_cols: List[str],
-    other_cols: Optional[List[str]] = None,
 ) -> Tuple[str, str]:
     """Validate the given submission has the right headers.
     It is recommended to use one of the following functions instead of this one:
@@ -42,7 +41,6 @@ def _validate_headers(
         submission -- pandas DataFrame of the submission
         expected_id_cols -- list of expected id columns
         expected_pred_cols -- list of expected prediction columns
-        other_cols -- optional list of other columns that can be present in the submission
 
     Return Tuple[str, str]:
         - string name of the id column
@@ -53,13 +51,6 @@ def _validate_headers(
         for ticker_col in expected_id_cols
         for signal_col in expected_pred_cols
     ]
-    if other_cols is not None:
-        expected_headers += [
-            [ticker_col, signal_col, other_col]
-            for ticker_col in expected_id_cols
-            for signal_col in expected_pred_cols
-            for other_col in other_cols
-        ]
     columns = submission.columns
     valid_headers = list(columns) in expected_headers
     assert valid_headers, (
@@ -77,13 +68,30 @@ def validate_headers_numerai(submission: pd.DataFrame) -> Tuple[str, str]:
     )
 
 
-def validate_headers_signals(submission: pd.DataFrame) -> Tuple[str, str]:
-    return _validate_headers(
+def validate_headers_signals(
+    submission: pd.DataFrame, assert_date_col: bool = False
+) -> Tuple[str, str, Optional[str]]:
+    # remove date columns if they exist and store them temporarily
+    date_col_name: Optional[str] = None
+    date_col: Optional[pd.Series] = None
+    for col in submission.columns:
+        if col in SIGNALS_ALLOWED_DATE_COLS:
+            date_col_name = col
+            date_col = submission[date_col_name].copy()
+            submission = submission.drop(columns=date_col_name, errors="ignore")
+            break
+    if assert_date_col:
+        assert (
+            date_col_name is not None
+        ), "invalid_submission_headers: submission must contain a date column"
+    ticker_col, signal_col = _validate_headers(
         submission,
         SIGNALS_ALLOWED_ID_COLS,
         SIGNALS_ALLOWED_PRED_COLS,
-        SIGNALS_ALLOWED_DATE_COLS,
     )
+    if date_col is not None:
+        submission[date_col_name] = date_col
+    return ticker_col, signal_col, date_col_name
 
 
 def validate_headers_crypto(submission: pd.DataFrame) -> Tuple[str, str]:
@@ -217,7 +225,7 @@ def validate_submission_signals(
             "Please remove the data_type column from your Signals submission."
         )
         submission = submission.drop(columns=["data_type"], errors="ignore")
-    ticker_col, signal_col = validate_headers_signals(submission)
+    ticker_col, signal_col, _ = validate_headers_signals(submission)
     filtered_sub, invalid_tickers = validate_ids_signals(
         universe[ticker_col], submission, ticker_col
     )
@@ -238,7 +246,6 @@ def validate_submission_crypto(
         Tuple[str, str, pd.DataFrame, List[str]] - the validated ticker column, signal column,
                                                    filtered submission, and list of invalid tickers
     """
-    print(universe)
     ticker_col, signal_col = validate_headers_crypto(submission)
     filtered_sub, invalid_tickers = validate_ids_crypto(
         universe[ticker_col], submission, ticker_col

{numerai_tools-0.5.0.dev5 → numerai_tools-0.5.0.dev6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "numerai-tools"
-version = "0.5.0.dev5"
+version = "0.5.0.dev6"
 description = "A collection of open-source tools to help interact with Numerai, model data, and automate submissions."
 authors = [
     {name = "Numerai Engineering",email = "engineering@numer.ai"}