flake8 and black reformatting, add missing backslash in docker build …

…script

docker/images/dashboard_image/.env

@@ -3,7 +3,7 @@ VERSION="latest"
 TAG="dash-${APP}-${VERSION}"
 DOCKER_REPO="alphasentaurii/spacekit"
 DOCKER_IMAGE="${DOCKER_REPO}:${TAG}"
-SPACEKIT_VERSION="0.3.2rc1"
+SPACEKIT_VERSION="0.3.2"
 SRC="pkg" # pkg, s3, git, file
 COLLECTION="calcloud" # bucketname, repo url, or local path
 DATASETS="2022-02-14,2021-11-04,2021-10-28"
@@ -17,4 +17,4 @@ DESTDATA="" #"/home/developer/spacekit"
 HOSTNAME="localhost"
 IPADDRESS=0.0.0.0
 NAME="spkt-dash-${APP}-${VERSION}"
-EPCOMMAND="python -m spacekit.dashboard.${APP}.index"
+EPCOMMAND="python -m spacekit.dashboard.${APP}.index"

docker/images/dashboard_image/Dockerfile

@@ -35,19 +35,20 @@ ENV SPACEKIT_VERSION=${SPACEKIT_VERSION}
 #   pip install --upgrade pip && \
 #   pip install -e . && \
 #   pip install \
-#     sklearn \
 #     dash~=2.0.0 \
 #     dash-cytoscape \
 #     dash-daq
 
-# # Install and test new spacekit release from git
-# RUN git clone https://github.com/alphasentaurii/spacekit.git && \
-#   cd /home/developer/spacekit && \
-#   git fetch --all --tags && \
-#   git checkout tags/${SPACEKIT_VERSION} && \
+# # Install and test spacekit release candidate from git
+# ENV SPACEKIT_BINARY=/home/developer/spacekit-${SPACEKIT_VERSION}.tar.gz
+# ENV SPACEKIT_SRC=/home/developer/spacekit-${SPACEKIT_VERSION}
+# ENV LOCATION https://github.com/alphasentaurii/spacekit/archive/refs/tags/${SPACEKIT_VERSION}.tar.gz
+# RUN curl -L -o $SPACEKIT_BINARY $LOCATION && \
+#   tar -xzvf $SPACEKIT_BINARY && rm $SPACEKIT_BINARY && \
+#   cd $SPACEKIT_SRC && \
+#   pip install --upgrade pip && \
 #   pip install -e . && \
 #   pip install \
-#     sklearn \
 #     dash~=2.0.0 \
 #     dash-cytoscape \
 #     dash-daq
@@ -83,6 +84,6 @@ ENV PFX=${PFX}
 ARG SRC
 ARG COLLECTION
 ARG DATASETS
-RUN python -m spacekit.datasets.beam -s="${SRC}:${COLLECTION}" -d=$DATASETS -o=$SPACEKIT_DATA
+# RUN python -m spacekit.datasets.beam -s="${SRC}:${COLLECTION}" -d=$DATASETS -o=$SPACEKIT_DATA
 EXPOSE 8050
 CMD /bin/bash

scripts/build.sh

@@ -4,7 +4,7 @@ source "./docker/images/dashboard_image/.env"
 DOCKER_FILE=./docker/images/dashboard_image/Dockerfile
 
 docker build -f ${DOCKER_FILE} -t ${DOCKER_IMAGE} \
---build-arg SPACEKIT_VERSION="${SPACEKIT_VERSION}"
+--build-arg SPACEKIT_VERSION="${SPACEKIT_VERSION}" \
 --build-arg SRC="${SRC}" \
 --build-arg COLLECTION="${COLLECTION}" \
 --build-arg PFX="${PFX}" \

spacekit/datasets/beam.py

@@ -35,6 +35,7 @@
 DATA = "spacekit.datasets.data"
 S3PREFIX = os.environ.get("PFX", "archive")
 
+
 def download(scrape="file:data", datasets="2022-02-14,2021-11-04,2021-10-28", dest="."):
     src, archive = scrape.split(":")
     datasets = datasets.split(",")
@@ -77,12 +78,17 @@ def download(scrape="file:data", datasets="2022-02-14,2021-11-04,2021-10-28", de
 
 if __name__ == "__main__":
     parser = argparse.ArgumentParser()
-    parser.add_argument("-s", "--scrape", default="git:calcloud", help="Uses a key:uri format where options for the key are limited to pkg, s3, file, or git and the uri could be your own custom location if not using the default datasets.  Examples are pkg:calcloud, git:repo_uri, s3:mybucket, file:myfolder. Visit spacekit.readthedocs.io for more info.")
+    parser.add_argument(
+        "-s",
+        "--scrape",
+        default="git:calcloud",
+        help="Uses a key:uri format where options for the key are limited to pkg, s3, file, or git and the uri could be your own custom location if not using the default datasets.  Examples are pkg:calcloud, git:repo_uri, s3:mybucket, file:myfolder. Visit spacekit.readthedocs.io for more info.",
+    )
     parser.add_argument(
         "-d",
         "--datasets",
         default="2022-02-14,2021-11-04,2021-10-28",
-        help="Comma-separated string of keys identifying each dataset"
+        help="Comma-separated string of keys identifying each dataset",
     )
     parser.add_argument("-o", "--out", default=None)
     args = parser.parse_args()

spacekit/datasets/meta.py

@@ -4,19 +4,19 @@
     "data": {
         "2022-02-14": {
             "fname": "2022-02-14-1644848448.zip",
-            "hash": "d39482d148736f2b2e8ad1ca19f0d6797bab6582700f174df0344fc9f91687dd"
+            "hash": "d39482d148736f2b2e8ad1ca19f0d6797bab6582700f174df0344fc9f91687dd",
         },
         "2021-11-04": {
             "fname": "2021-11-04-1636048291.zip",
-            "hash": "d0cb8c35554527d8dda96f259952b0d1436f6fda5f4d11ced73d7e88f328aff4"
+            "hash": "d0cb8c35554527d8dda96f259952b0d1436f6fda5f4d11ced73d7e88f328aff4",
         },
         "2021-10-28": {
             "fname": "2021-10-28-1635457222.zip",
-            "hash": "dce221998c366486e3412b13ad90493bad6e234d54e0849a635700cb8494acb4"
+            "hash": "dce221998c366486e3412b13ad90493bad6e234d54e0849a635700cb8494acb4",
         },
         "2021-08-22": {
             "fname": "2021-08-22-1629663047.zip",
-            "hash": "d8f17819282add50c3c27fc8eada314ffad72a60c8b0e8639d98b5f6f77602bb"
+            "hash": "d8f17819282add50c3c27fc8eada314ffad72a60c8b0e8639d98b5f6f77602bb",
         },
     },
     "model": {
@@ -32,7 +32,7 @@
         "2022-02-14": {
             "fname": "2022-02-14-1644850390.zip",
             "hash": "7f5ad34c2265219dd62eeb9a79612e69b2b1daf36735d2f9803898cfd1944dd7",
-            "desc": "ensembleSVM training results"
+            "desc": "ensembleSVM training results",
         },
         "2022-01-30": {
             "fname": "2022-01-30-1643523529.zip",

spacekit/preprocessor/encode.py

@@ -263,41 +263,6 @@ def svm_keypairs(self, column):
         }
         return keypairs[column]
 
-    def set_detector_keys(self):
-        """Assigns a hardcoded integer to each 'detector' key in alphabetical and increasing value.
-
-        Returns
-        -------
-        dict
-            detector names and their associated integer encoding
-        """
-        self.detector_keys = {"hrc": 0, "ir": 1, "sbc": 2, "uvis": 3, "wfc": 4}
-        return self.detector_keys
-
-    def set_wcs_keys(self):
-        """Assigns a hardcoded integer to each 'wcs' key in alphabetical and increasing value.
-
-        Returns
-        -------
-        _type_
-            _description_
-        """
-        self.wcs_keys = {
-            "a posteriori": 0,
-            "a priori": 1,
-            "default a": 2,
-            "not aligned": 3,
-        }
-        return self.wcs_keys
-
-    def svm_keypairs(self, column):
-        keypairs = {
-            "category": self.category_keys,
-            "detector": self.detector_keys,
-            "wcstype": self.wcs_keys,
-        }
-        return keypairs[column]
-
     def encode_categories(self, cname="category", sep=";"):
         """Transforms the raw string inputs from MAST target category naming conventions into an abbreviated form. For example, `CLUSTER OF GALAXIES;GRAVITATIONA` becomes `GC` for galaxy cluster; and `STELLAR CLUSTER;GLOBULAR CLUSTER` becomes `SC` for stellar cluster. This serves to group similar but differently named objects into a discrete set of 8 possible categorizations. The 8 categories will then be encoded into integer values in the final encoding step (machine learning inputs must be numeric).
 
@@ -356,9 +321,9 @@ def display_encoding(self):
                 )
             )
             print(f"\n{k}<--->{v}\n")
-            print(f"#VAL\t\tENC\t\t#VAL\t\tORDINAL")
+            print("#VAL\t\tENC\t\t#VAL\t\tORDINAL")
             for r in res:
-                string = f"\t\t".join(str(i) for i in r)
+                string = "\t\t".join(str(i) for i in r)
                 print(string)
             print("\n")
         print("---" * 7)

spacekit/preprocessor/scrub.py

@@ -59,7 +59,6 @@ def rename_cols(self, old=None, new=None):
 
     def drop_nans(self, save_backup=True):
         if self.dropnans is True:
-            df_nan = self.df.copy()
             print("Searching for NaNs...")
             print(self.df.isna().sum())
             if self.df.isna().sum().values.any() > 0: