sovai 0.2.35__tar.gz → 0.2.38__tar.gz

{sovai-0.2.35 → sovai-0.2.38}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.3
 Name: sovai
-Version: 0.2.35
+Version: 0.2.38
 Summary: python for asset management
 License: Proprietary License
 Author: Derek Snow
@@ -30,7 +30,7 @@ Requires-Dist: openai (>=1.0) ; extra == "full"
 Requires-Dist: pandas (>=1.0)
 Requires-Dist: pexpect (>=4.9.0) ; extra == "full"
 Requires-Dist: plotly (>=5.0) ; extra == "full"
-Requires-Dist: polars (>=0.20.30)
+Requires-Dist: polars (>=1.2,<2.0)
 Requires-Dist: polars-talib (==0.1.3) ; extra == "full"
 Requires-Dist: pyarrow (>=5.0)
 Requires-Dist: python-dateutil (>=2.8)

{sovai-0.2.35 → sovai-0.2.38}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "sovai"
-version = "0.2.35"
+version = "0.2.38"
 description = "python for asset management"
 authors = ["Derek Snow <d.snow@outlook.com>"]
 license = "Proprietary License"
@@ -37,7 +37,7 @@ pyarrow = ">=5.0"
 requests = ">=2.20"
 python-dateutil = ">=2.8"
 python-dotenv = ">=0.10"
-polars = ">=0.20.30"
+polars = "^1.2"
 boto3 = ">=1.20"
 joblib = ">=1.0"
 rapidfuzz = "^3.9.7"

sovai-0.2.35/sovai/get_data.py → sovai-0.2.38/sovai/get_data copy.py

@@ -20,8 +20,11 @@ from sovai.errors.sovai_errors import InvalidInputData
 from sovai.utils.converter import convert_data2df
 from sovai.utils.stream import stream_data, stream_data_pyarrow
 from sovai.utils.datetime_formats import datetime_format
+
 from sovai.utils.client_side import client_side_frame
 from sovai.utils.client_side_s3 import load_frame_s3
+from sovai.utils.client_side_s3_part_high import load_frame_s3_partitioned_high
+
 
 ## Note run these for TEST - IT COULD BE HERE some silent problems
 try:
@@ -234,9 +237,9 @@ endpoint_to_ticker = {
     "/news/sentiment_score": None,
     "/insider/trading": "",
     "/wikipedia/views": "",
-    "/spending/contracts": "",
+    # "/spending/contracts": "",
     "/spending/details": "",
-    "/spending/transactions": "",
+    # "/spending/transactions": "",
     "/spending/products": "",
     "/spending/location": "",
     "/spending/compensation": "",
@@ -296,6 +299,9 @@ def normalize_endpoint(endpoint):
 
 ## If you also want access by full file, please also add to endpoint_to_ticker
 
+
+
+# Define your endpoint sets
 client_side_endpoints_gcs = {
     "ratios/relative",
     "market/prices",
@@ -306,7 +312,6 @@ client_side_endpoints_gcs = {
     "lobbying/public",
 }
 
-## If you also want access by full file, please also add to endpoint_to_ticker
 client_side_endpoints_s3 = {
     "sec/10k",
     "trials/predict",
@@ -314,9 +319,23 @@ client_side_endpoints_s3 = {
     "trials/all/predict",
     "trials/all/decribe",
     "trials/all",
+}
+
+client_side_endpoints_s3_part_high = {
+    "patents/applications",
+    "patents/grants",
+    "clinical_trials",
+    "spending/awards"
+
 
 }
 
+# Create a list of handlers
+handlers = [
+    (client_side_endpoints_gcs, client_side_frame, "Grabbing GCS client side"),
+    (client_side_endpoints_s3, load_frame_s3, "Grabbing S3 client side"),
+    (client_side_endpoints_s3_part_high, load_frame_s3_partitioned_high, "Grabbing S3 Partitioned High client side"),
+]
 
 
 # In your main function or wherever this logic is implemented:
@@ -604,26 +623,22 @@ def data(
 
     normalized_endpoint = normalize_endpoint(endpoint)
 
-    if (
-        normalized_endpoint in client_side_endpoints_gcs
-        and tickers is not None
-        and frequency is None
-    ):
-        verbose_mode.vprint("Grabbing gcs client side")
-        _query_cache[cache_key] = client_side_frame(
-            normalized_endpoint, tickers, columns, start_date, end_date
-        )
-        return _query_cache[cache_key]
+    # ACTAULLY I DON'T CARE, TICKERS CAN BE NONE FOR PATENTS
+
+    # Iterate through the handlers to find a matching handler
+    for endpoint_set, handler_func, message in handlers:
+        if (
+            normalized_endpoint in endpoint_set and
+            (tickers is not None or start_date is not None) and
+            frequency is None
+        ):
+            verbose_mode.vprint(message)
+            _query_cache[cache_key] = handler_func(
+                normalized_endpoint, tickers, columns, start_date, end_date
+            )
+            return _query_cache[cache_key]
+
 
-    elif (
-        normalized_endpoint in client_side_endpoints_s3
-        and tickers is not None
-        and frequency is None
-    ):
-        verbose_mode.vprint("Grabbing s3 client side")
-        _query_cache[cache_key] = load_frame_s3(
-            normalized_endpoint, tickers, columns, start_date, end_date)
-        return _query_cache[cache_key]
     try:
         if tickers is not None and not is_all(tickers):
             params = ticker_mapper(params,verbose)