Merge pull request #115 from /issues/114

Fix ingesting bug that creates one file per table

cytominer_database/ingest.py

@@ -99,12 +99,11 @@ def into(input, output, name, identifier, skip_table_prefix=False):
             #     deprecated, use inspect.signature() or inspect.getfullargspec()
             warnings.simplefilter("ignore", category=DeprecationWarning)
 
-            target = "{}::{}".format(output, name)
-            engine = create_engine(target)
+            engine = create_engine(output)
             con = engine.connect()
 
             df = pd.read_csv(source, index_col=0)
-            df.to_sql(name=target, con=con, if_exists="append")
+            df.to_sql(name=name, con=con, if_exists="append")
 
 def checksum(pathname, buffer_size=65536):
     """

tests/commands/test_command_ingest.py

@@ -45,11 +45,11 @@ def test_run(dataset, runner):
         for blob in dataset["ingest"]:
             table_name = blob["table"].capitalize()
 
-            target = "sqlite:///{}::{}".format(str(sqlite_file), table_name)
+            target = "sqlite:///{}".format(str(sqlite_file))
             engine = create_engine(target)
             con = engine.connect()
 
-            df = pd.read_sql(target, con=con, index_col=0)
+            df = pd.read_sql(sql=table_name, con=con, index_col=0)
 
             assert df.shape[0] == blob["nrows"]
             assert df.shape[1] == blob["ncols"] + 1
@@ -80,11 +80,11 @@ def test_run_defaults(cellpainting, runner):
         for blob in cellpainting["ingest"]:
             table_name = blob["table"].capitalize()
 
-            target = "sqlite:///{}::{}".format(str(sqlite_file), table_name)
+            target = "sqlite:///{}".format(str(sqlite_file))
             engine = create_engine(target)
             con = engine.connect()
 
-            df = pd.read_sql(target, con=con, index_col=0)
+            df = pd.read_sql(sql=table_name, con=con, index_col=0)
 
             assert df.shape[0] == blob["nrows"]
             assert df.shape[1] == blob["ncols"] + 1

tests/conftest.py

@@ -18,6 +18,12 @@ def pytest_generate_tests(metafunc):
 
 @pytest.fixture
 def cellpainting():
+    """
+    Return configuration for a Cell Painting dataset.
+    - 3 compartments CSVs: Cells, Cytoplasm, Nuclei
+    - 1 image CSV
+    - No object.csv and therefore no munging
+    """
     return {
         "config": "config.ini",
         "data_dir": "tests/data_b",
@@ -49,6 +55,12 @@ def cellpainting():
 
 @pytest.fixture
 def htqc():
+    """
+    Return configuration for a 3-channel image-based profiling dataset.
+    - 1 object CSV that comprises Cells, Cytoplasm, Nuclei
+    - 1 image CSV
+    - munging required
+    """
     return {
         "config": "config.ini",
         "data_dir": "tests/data_a",
@@ -82,6 +94,11 @@ def htqc():
 
 @pytest.fixture
 def qc():
+    """
+    Return configuration for a QC dataset (only image table, no objects).
+    - 1 image CSV
+    - No object.csv and therefore no munging
+    """
     return {
         "config": None,
         "data_dir": "tests/data_c",

tests/test_ingest.py

@@ -27,14 +27,16 @@ def test_seed(dataset):
             target="sqlite:///{}".format(str(sqlite_file))
         )
 
+        assert os.path.exists(str(sqlite_file))
+
         for blob in ingest:
             table_name = blob["table"].capitalize()
 
-            target = "sqlite:///{}::{}".format(str(sqlite_file), table_name)
+            target = "sqlite:///{}".format(str(sqlite_file))
             engine = create_engine(target)
             con = engine.connect()
 
-            df = pd.read_sql(target, con=con, index_col=0)
+            df = pd.read_sql(sql=table_name, con=con, index_col=0)
 
             assert df.shape[0] == blob["nrows"]
             assert df.shape[1] == blob["ncols"] + 1