Rename functions

crocodeel/__init__.py

@@ -0,0 +1,3 @@
+import os
+# Disable implicit parallelism in numpy
+os.environ["OMP_NUM_THREADS"] = "1"

crocodeel/ab_table_utils.py

@@ -4,48 +4,46 @@
 import sys
 from typing import TextIO
 
-class SpeciesAbTableUtils:
-    @staticmethod
-    def load(fh: TextIO) -> pd.DataFrame:
-        # Read table
-        species_ab_table = pd.read_csv(fh, sep="\t", header=0, index_col=0)
-        logging.info(
-            "Abundance table quantifies %d species in %d samples", species_ab_table.shape[0], species_ab_table.shape[1]
+
+def load(fh: TextIO) -> pd.DataFrame:
+    # Read table
+    species_ab_table = pd.read_csv(fh, sep="\t", header=0, index_col=0)
+    logging.info(
+        "Abundance table quantifies %d species in %d samples", species_ab_table.shape[0], species_ab_table.shape[1]
+    )
+
+    # Check species names
+    species_names_type = species_ab_table.index.inferred_type
+    if species_names_type not in ("integer", "string"):
+        logging.error(
+            "Species names in first column are of the '%s' type but should be 'string' or 'integer'",
+            species_names_type,
         )
+        sys.exit(1)
+    # Convert species names to strings when they are integers
+    species_ab_table.index = species_ab_table.index.astype(str)
+
+    # Check species abundance type
+    bad_format_samples = [
+        sample
+        for sample in species_ab_table.columns
+        if not pd.api.types.is_numeric_dtype(species_ab_table[sample].dtype)
+    ]
+    if bad_format_samples:
+        logging.error("Species abundance in the following samples is not numeric: %s", " ".join(bad_format_samples))
+        sys.exit(1)
+
+
 
-        # Check species names
-        species_names_type = species_ab_table.index.inferred_type
-        if species_names_type not in ("integer", "string"):
-            logging.error(
-                "Species names in first column are of the '%s' type but should be 'string' or 'integer'",
-                species_names_type,
-            )
-            sys.exit(1)
-        # Convert species names to strings when they are integers
-        species_ab_table.index = species_ab_table.index.astype(str)
-
-        # Check species abundance type
-        bad_format_samples = [
-            sample
-            for sample in species_ab_table.columns
-            if not pd.api.types.is_numeric_dtype(species_ab_table[sample].dtype)
-        ]
-        if bad_format_samples:
-            logging.error("Species abundance in the following samples is not numeric: %s", " ".join(bad_format_samples))
-            sys.exit(1)
-
-
-
-        return species_ab_table
+    return species_ab_table
 
-    @staticmethod
-    def normalize(species_ab_table: pd.DataFrame) -> pd.DataFrame :
-        # Normalize to relative abundance
-        species_ab_table = species_ab_table.div(species_ab_table.sum(axis=0), axis=1)
+def normalize(species_ab_table: pd.DataFrame) -> pd.DataFrame :
+    # Normalize to relative abundance
+    species_ab_table = species_ab_table.div(species_ab_table.sum(axis=0), axis=1)
 
-        # Perform log10 transformation
-        with np.errstate(divide="ignore"):
-            species_ab_table = species_ab_table.apply(np.log10)
+    # Perform log10 transformation
+    with np.errstate(divide="ignore"):
+        species_ab_table = species_ab_table.apply(np.log10)
 
-        logging.info("Species abundance table normalized and log-transformed")
-        return species_ab_table
+    logging.info("Species abundance table normalized and log-transformed")
+    return species_ab_table

crocodeel/easy_wf.py

@@ -1,12 +1,12 @@
 from typing import Any
-from crocodeel.species_ab_table import SpeciesAbTableUtils
+import crocodeel.ab_table_utils as ab_table_utils
 from crocodeel.search_conta import run_search_conta
 from crocodeel.plot_conta import run_plot_conta, Defaults as plot_conta_defaults
 
 def run_easy_wf(args: dict[str,Any]):
-    species_ab_table = SpeciesAbTableUtils.load(args["species_ab_table_fh"])
+    species_ab_table = ab_table_utils.load(args["species_ab_table_fh"])
     args["species_ab_table_fh"].close()
-    args["species_ab_table"] = SpeciesAbTableUtils.normalize(species_ab_table)
+    args["species_ab_table"] = ab_table_utils.normalize(species_ab_table)
 
     run_search_conta(args)
 

crocodeel/plot_conta.py

@@ -8,16 +8,16 @@
 import logging
 from time import perf_counter
 from crocodeel.conta_event import ContaminationEvent, ContaminationEventIO
-from crocodeel.species_ab_table import SpeciesAbTableUtils
+import crocodeel.ab_table_utils as ab_table_utils
 
 
 def run_plot_conta(args: dict[str, Any]):
     if "species_ab_table" in args:
         species_ab_table = args["species_ab_table"]
     else:
-        species_ab_table = SpeciesAbTableUtils.load(args["species_ab_table_fh"])
+        species_ab_table = ab_table_utils.load(args["species_ab_table_fh"])
         args["species_ab_table_fh"].close()
-        species_ab_table = SpeciesAbTableUtils.normalize(species_ab_table)
+        species_ab_table = ab_table_utils.normalize(species_ab_table)
 
     conta_events = list(ContaminationEventIO.read_tsv(args["conta_events_fh"]))
     if args["conta_events_fh"].mode == 'r':

crocodeel/search_conta.py

@@ -1,5 +1,3 @@
-import os
-os.environ["OMP_NUM_THREADS"] = "1"
 from multiprocessing import Pool
 from functools import partial
 from itertools import product
@@ -13,7 +11,7 @@
 from sklearn.metrics import mean_squared_error
 from sklearn.neighbors import NearestNeighbors
 from scipy.stats import spearmanr
-from crocodeel.species_ab_table import SpeciesAbTableUtils
+import crocodeel.ab_table_utils as ab_table_utils
 from crocodeel.conta_event import ContaminationEvent, ContaminationEventIO
 from crocodeel.rf_model import RandomForestModel
 
@@ -23,9 +21,9 @@ def run_search_conta(args: dict[str,Any]):
     if "species_ab_table" in args:
         species_ab_table = args["species_ab_table"]
     else:
-        species_ab_table = SpeciesAbTableUtils.load(args["species_ab_table_fh"])
+        species_ab_table = ab_table_utils.load(args["species_ab_table_fh"])
         args["species_ab_table_fh"].close()
-        species_ab_table = SpeciesAbTableUtils.normalize(species_ab_table)
+        species_ab_table = ab_table_utils.normalize(species_ab_table)
 
     start = perf_counter()
     logging.info("Search for contaminations started")