Implementing parquet loading in load_profiles function

pycytominer/cyto_utils/load.py

@@ -1,8 +1,48 @@
 import csv
 import gzip
+from pathlib import Path
 import numpy as np
 import pandas as pd
 
+def is_path_a_parquet_file(file: str) -> bool:
+    """Checks if the provided file path is a parquet file.
+
+    Identification of parquet files are done by inspecting the file extensions. 
+    If the file does not end with `parquet`, this will return False, else True. 
+
+    Parameters
+    ----------
+    file : str
+        path to parquet file
+
+    Returns
+    -------
+    bool
+        Returns True if the file path contains `.parquet`, else it will return
+        False
+
+    Raises
+    ------
+    TypeError
+        Raised if a non str object is passed in the `file` parameter
+    FileNotFoundError
+        Raised if the provided path in the `file` does not exist 
+    """
+    # type checking
+    if not isinstance(file, str):
+        raise TypeError(f"file must be a str not {type(file)}")
+
+    # converting str object to Path Object
+    # -- checking if it exists
+    file = Path(file)
+    if not file.exists():
+        raise FileNotFoundError(f"{str(file.absolute())} does not exists")
+
+    # checking if file path is a parquet file
+    if not file.suffix.lower() == ".parquet":
+        return False
+    return  True
+
 
 def infer_delim(file):
     """
@@ -41,20 +81,25 @@ def load_profiles(profiles):
     Return
     ------
     pandas DataFrame of profiles
+
+    Raises
+    ------
+    FileNotFoundError
+        Raised if the provided
     """
     if not isinstance(profiles, pd.DataFrame):
-        try:
-            delim = infer_delim(profiles)
-            profiles = pd.read_csv(profiles, sep=delim)
-        except FileNotFoundError:
-            raise FileNotFoundError(f"{profiles} profile file not found")
+
+        if is_path_a_parquet_file(profiles):
+            return pd.read_parquet(profiles, engine="pyarrow")
+
+        delim = infer_delim(profiles)
+        profiles = pd.read_csv(profiles, sep=delim)
+
     return profiles
 
 
 def load_platemap(platemap, add_metadata_id=True):
     """
-    Unless a dataframe is provided, load the given platemap dataframe from path or string
-
     Parameters
     ----------
     platemap : pandas dataframe

pycytominer/tests/test_cyto_utils/test_load.py

@@ -10,7 +10,8 @@
     load_npz_features,
     load_npz_locations,
 )
-from pycytominer.cyto_utils.load import infer_delim
+from pycytominer.cyto_utils.load import (infer_delim,
+                                         is_path_a_parquet_file)
 
 random.seed(123)
 
@@ -196,3 +197,22 @@ def test_load_npz():
         load_npz_locations(
             example_npz_file_locations, location_x_col_index=0, location_y_col_index=2
         )
+
+def test_infer_plate_files():
+
+    # file paths
+    csv_file = "../test_data/cytominer_database_example_data/test_SQ00014613.csv.gz"
+    parquet_file = "../test_data/cytominer_database_example_data/test_SQ00014613.parquet"
+
+    # checking parquet file
+    check_pass = is_path_a_parquet_file(parquet_file)
+    check_fail = is_path_a_parquet_file(csv_file)
+
+    # checking if the correct booleans are returned
+    assert(check_pass, True)
+    assert(check_fail, False)
+
+    # loading in pandas dataframe from parquet file
+    parquet_df = pd.read_parquet(parquet_file)
+    parquet_profile_test = load_profiles(parquet_file)
+    pd.testing.assert_frame_equal(parquet_profile_test, parquet_df)