Remove Pandera as dependency

cutouts/filter.py

@@ -1,17 +1,15 @@
 import logging
 
 import numpy as np
-import pandera as pa
-from pandera.typing import DataFrame
+import pandas as pd
 
-from .io.types import CutoutRequest, CutoutResult, CutoutsResultSchema
+from .io.types import CutoutRequest, CutoutResult
 
 logger = logging.getLogger(__file__)
 
 
-@pa.check_types
 def select_cutout(
-    results_df: DataFrame[CutoutsResultSchema], cutout_request: CutoutRequest
+    results_df: pd.DataFrame, cutout_request: CutoutRequest
 ) -> CutoutResult:
     """
     Select the cutout closest to the requested exposure start time +- delta_time.
@@ -91,9 +89,8 @@ def select_cutout(
     return result
 
 
-@pa.check_types
 def select_comparison_cutout(
-    results_df: DataFrame[CutoutsResultSchema],
+    results_df: pd.DataFrame,
     cutout_result: CutoutResult,
     cutout_request: CutoutRequest,
     min_time_separation: float = 1 / 24,

cutouts/io/nsc.py

@@ -1,11 +1,9 @@
 import logging
 
-import pandera as pa
-from pandera.typing import DataFrame
+import pandas as pd
 from pyvo.dal.sia import SIAResults
 
 from .sia import SIAHandler
-from .types import CutoutRequest, CutoutsResultSchema
 from .util import exposure_id_from_url
 
 logger = logging.getLogger(__name__)
@@ -16,10 +14,9 @@ def _get_generic_image_url_from_cutout_url(cutout_url: str):
     return cutout_url.split("&POS=")[0]
 
 
-@pa.check_types
 def find_cutouts_nsc_dr2(
-    cutout_request: CutoutRequest,
-) -> DataFrame[CutoutsResultSchema]:
+    cutout_request: pd.DataFrame,
+) -> pd.DataFrame:
     """
     Search the NOIRLab Archive for cutouts and images at a given RA, Dec.
 

cutouts/io/skymapper.py

@@ -1,12 +1,10 @@
 import logging
 
 import pandas as pd
-import pandera as pa
-from pandera.typing import DataFrame
 from pyvo.dal.sia import SIAResults
 
 from .sia import SIAHandler
-from .types import CutoutRequest, CutoutsResultSchema
+from .types import CutoutRequest
 
 logger = logging.getLogger(__name__)
 
@@ -22,10 +20,9 @@ def _get_generic_image_url_from_cutout_url(cutout_url: str):
     return url_string
 
 
-@pa.check_types
 def find_cutouts_skymapper_dr2(
     cutout_request: CutoutRequest,
-) -> DataFrame[CutoutsResultSchema]:
+) -> pd.DataFrame:
     """
     Search the Skymapper SIA service for cutouts and images at a given RA, Dec.
 

cutouts/io/tests/test_nsc_dr2.py

@@ -1,11 +1,15 @@
 import os
 from contextlib import contextmanager
 from unittest.mock import patch
+import pathlib
+import pickle
+import pandas as pd
 
 from astropy.io.votable import parse
 from pyvo.dal.sia import SIAResults
 
 from ..nsc import NSC_DR2_SIA, find_cutouts_nsc_dr2
+from ...main import get_cutouts
 from ..types import CutoutRequest
 
 # 2014 HE199 (2014-04-28T08:07:52.435)
@@ -67,3 +71,23 @@ def test_sia_nsc_dr2_query():
             assert col in results.columns
 
         assert "VR" in results["filter"].values
+
+
+def test_sia_nsc_dr2_query_():
+
+    with mock_sia_nsc_dr2_query(
+        "nsc_dr2_227.5251615214173_-27.026013823449265_56775.33880132809.xml"
+    ) as mock:
+        results, comparison_results = get_cutouts(
+            pd.DataFrame(cutout_request1),
+            out_dir=pathlib.Path(os.path.dirname(os.path.abspath(__file__)))
+        )
+        print(results)
+        print(comparison_results)
+
+        with open('cutout_results.pickle', 'wb') as f:
+            pickle.dump(results, f)
+        with open('cutout_comparison_results.pickle', 'wb') as f:
+            pickle.dump(comparison_results, f)
+
+        assert False

cutouts/io/types.py

@@ -1,50 +1,8 @@
 from typing import Optional
 
-import pandera as pa
-from pandera.typing import Series
 from pydantic import BaseModel
 
 
-class CutoutRequestSchema(pa.SchemaModel):
-    """
-    Dataframe validation for multiple cutout requests
-    """
-
-    request_id: Optional[Series[str]] = pa.Field(nullable=True)
-    observatory_code: Series[str] = pa.Field(coerce=True)
-    exposure_start_mjd: Series[float] = pa.Field(nullable=False, coerce=True)
-    ra_deg: Series[float] = pa.Field(ge=0, le=360, coerce=True)
-    dec_deg: Series[float] = pa.Field(ge=-90, le=90, coerce=True)
-    filter: Optional[
-        Series[str]
-    ] = pa.Field()  # TODO: validate against real list of filters?
-    exposure_id: Optional[Series[str]] = pa.Field(nullable=True)
-    exposure_duration: Optional[Series[float]] = pa.Field(
-        ge=0, le=2000, coerce=True, nullable=True
-    )
-    height_arcsec: Series[float] = pa.Field(ge=0, le=200, coerce=True, nullable=True)
-    width_arcsec: Series[float] = pa.Field(ge=0, le=200, coerce=True, nullable=True)
-    delta_time: Series[float] = pa.Field(ge=0, le=100, coerce=True, nullable=True)
-
-
-class CutoutsResultSchema(pa.SchemaModel):
-    # TODO: ra, dec here are the ra, dec returned by the query and
-    # these should be equal to the queried ra and dec.
-    # However, this may not always be true and we may want to consider
-    # adding additional fields to allow backends to return things such as the
-    # the center of the image/cutout.
-    ra_deg: Series[float] = pa.Field(ge=0, le=360, coerce=True)
-    dec_deg: Series[float] = pa.Field(ge=-90, le=90, coerce=True)
-    filter: Series[str] = pa.Field()
-    exposure_id: Series[str] = pa.Field()
-    exposure_start_mjd: Series[float] = pa.Field(nullable=False, coerce=True)
-    exposure_duration: Series[float] = pa.Field(ge=0, le=2000, coerce=True)
-    cutout_url: Series[str] = pa.Field(coerce=True)
-    image_url: Series[str] = pa.Field(coerce=True)
-    height_arcsec: Series[float] = pa.Field(ge=0, le=200, coerce=True)
-    width_arcsec: Series[float] = pa.Field(ge=0, le=200, coerce=True)
-
-
 class CutoutRequest(BaseModel):
     """
     A single cutout request

cutouts/io/ztf.py

@@ -5,11 +5,9 @@
 import backoff
 import numpy as np
 import pandas as pd
-import pandera as pa
 import requests
-from pandera.typing import DataFrame
 
-from .types import CutoutRequest, CutoutsResultSchema
+from .types import CutoutRequest
 
 logger = logging.getLogger(__file__)
 
@@ -83,8 +81,7 @@ def perform_request(search_url):
     return response.text
 
 
-@pa.check_types()
-def find_cutouts_ztf(cutout_request: CutoutRequest) -> DataFrame[CutoutsResultSchema]:
+def find_cutouts_ztf(cutout_request: CutoutRequest) -> pd.DataFrame:
     """
     Search the ZTF service for cutouts and images at a given RA, Dec.
 

cutouts/main.py

@@ -2,17 +2,15 @@
 import logging
 import pathlib
 import sys
-from typing import Any, Dict, Iterable, Optional, Tuple, cast
+from typing import Any, Dict, Iterable, Optional, Tuple
 
 import numpy as np
 import pandas as pd
-import pandera as pa
 from astropy.time import Time
-from pandera.typing import DataFrame
 
 from .filter import select_comparison_cutout, select_cutout
 from .io import download_cutout, find_cutouts
-from .io.types import CutoutRequest, CutoutRequestSchema
+from .io.types import CutoutRequest
 from .plot import generate_gif, plot_comparison_cutouts, plot_cutouts
 
 logger = logging.getLogger("cutouts")
@@ -27,9 +25,8 @@
 }
 
 
-@pa.check_types
 def get_cutouts(
-    cutout_requests: DataFrame[CutoutRequestSchema],
+    cutout_requests: pd.DataFrame,
     out_dir: pathlib.Path,
     timeout: Optional[int] = 180,
     full_image_timeout: Optional[int] = 600,
@@ -226,7 +223,6 @@ def run_cutouts_from_precovery(
     compare: bool = False,
     compare_kwargs: Optional[dict] = None,
 ):
-
     # This seems unecessary but linting fails without it
     out_dir_path = pathlib.Path(str(out_dir))
     out_file_path = pathlib.Path(str(out_file))
@@ -268,7 +264,7 @@ def run_cutouts_from_precovery(
     cutout_requests["delta_time"].fillna(1e-8, inplace=True)
 
     cutout_results, comparison_results = get_cutouts(
-        cast(DataFrame[CutoutRequestSchema], cutout_requests),
+        cutout_requests,
         out_dir=out_dir_path,
         download_full_image=download_full_image,
         timeout=timeout,

requirements.txt

@@ -1,15 +1,119 @@
-astropy
-backoff
-numpy
-pandas
-pandera
-pyvo
-matplotlib
-multimethod>=1.9.1
-imageio
-pytest
-pytest-cov
-pre-commit
-setuptools>=45
-wheel
-setuptools_scm>=6.0
+#
+# This file is autogenerated by pip-compile with Python 3.11
+# by the following command:
+#
+#    pip-compile --all-extras
+#
+annotated-types==0.6.0
+    # via pydantic
+astropy==6.0.0
+    # via
+    #   cutouts (pyproject.toml)
+    #   pyvo
+astropy-iers-data==0.2024.1.22.0.30.30
+    # via astropy
+backoff==2.2.1
+    # via cutouts (pyproject.toml)
+certifi==2023.11.17
+    # via requests
+cfgv==3.4.0
+    # via pre-commit
+charset-normalizer==3.3.2
+    # via requests
+contourpy==1.2.0
+    # via matplotlib
+coverage[toml]==7.4.0
+    # via
+    #   coverage
+    #   pytest-cov
+cycler==0.12.1
+    # via matplotlib
+distlib==0.3.8
+    # via virtualenv
+filelock==3.13.1
+    # via virtualenv
+fonttools==4.47.2
+    # via matplotlib
+identify==2.5.33
+    # via pre-commit
+idna==3.6
+    # via requests
+imageio==2.33.1
+    # via cutouts (pyproject.toml)
+iniconfig==2.0.0
+    # via pytest
+kiwisolver==1.4.5
+    # via matplotlib
+matplotlib==3.8.2
+    # via cutouts (pyproject.toml)
+nodeenv==1.8.0
+    # via pre-commit
+numpy==1.26.3
+    # via
+    #   astropy
+    #   contourpy
+    #   cutouts (pyproject.toml)
+    #   imageio
+    #   matplotlib
+    #   pandas
+    #   pyerfa
+packaging==23.2
+    # via
+    #   astropy
+    #   matplotlib
+    #   pytest
+pandas==2.2.0
+    # via cutouts (pyproject.toml)
+pillow==10.2.0
+    # via
+    #   imageio
+    #   matplotlib
+platformdirs==4.1.0
+    # via virtualenv
+pluggy==1.4.0
+    # via pytest
+pre-commit==3.6.0
+    # via cutouts (pyproject.toml)
+pydantic==2.5.3
+    # via cutouts (pyproject.toml)
+pydantic-core==2.14.6
+    # via pydantic
+pyerfa==2.0.1.1
+    # via astropy
+pyparsing==3.1.1
+    # via matplotlib
+pytest==7.4.4
+    # via
+    #   cutouts (pyproject.toml)
+    #   pytest-cov
+pytest-cov==4.1.0
+    # via cutouts (pyproject.toml)
+python-dateutil==2.8.2
+    # via
+    #   matplotlib
+    #   pandas
+pytz==2023.3.post1
+    # via pandas
+pyvo==1.5
+    # via cutouts (pyproject.toml)
+pyyaml==6.0.1
+    # via
+    #   astropy
+    #   pre-commit
+requests==2.31.0
+    # via pyvo
+six==1.16.0
+    # via python-dateutil
+typing-extensions==4.9.0
+    # via
+    #   pydantic
+    #   pydantic-core
+tzdata==2023.4
+    # via pandas
+urllib3==2.1.0
+    # via requests
+virtualenv==20.25.0
+    # via pre-commit
+
+# The following packages are considered to be unsafe in a requirements file:
+# setuptools

setup.cfg

@@ -39,7 +39,6 @@ install_requires =
     pyvo
     matplotlib
     imageio
-    pandera
     pydantic
 
 [options.extras_require]