refactor: outputs to file in ./plots, updated cli and tests

.gitignore

@@ -156,4 +156,7 @@ dmypy.json
 # Cython debug symbols
 cython_debug/
 
+# VSCode
+.vscode/
+
 # End of https://www.toptal.com/developers/gitignore/api/python,git
\ No newline at end of file

requirements.txt

+matplotlib

requirements_dev.txt

@@ -3,4 +3,5 @@ flake8
 flake8-docstrings
 mypy
 pandas
-pytest
\ No newline at end of file
+pytest
+matplotlib

src/cli_plot_read_counts.py

+"""CLI for plot_read_counts function."""
+
+import argparse
+import logging
+
+from plot_read_counts import plot_read_counts
+
+
+def main():
+    r"""CLI for plot_read_counts.
+
+    This cli is used to access the functionality of plot_read_counts,
+    taking in a path of csv files, a gene ID, and an optional save
+    file name.
+
+    Typical example usage:
+
+    cli_plot_read_counts.py '../tests/resources' GENE1 '../test/PLSe1writeTarget.test'
+    """
+    parser = argparse.ArgumentParser(
+        description='number of transcripts to sample')
+    parser.add_argument('file_path', action='store',
+                        type=str, help='path to gene count .csv files')
+    parser.add_argument('gene_id', action='store',
+                        type=str, help='gene ID of which to plot counts')
+    argsin = parser.parse_args()
+
+    logging.basicConfig(format='[%(asctime)s: %(levelname)s] "%(module)s" %(message)s',
+                        level=logging.INFO)
+
+    plot_read_counts(argsin.file_path, argsin.gene_id)
+
+
+if __name__ == "__main__":
+    main()

src/plot_read_counts.py

@@ -3,19 +3,19 @@
 import logging
 from pathlib import Path
 from typing import Union
+from datetime import datetime
+
 import pandas
 import matplotlib.pyplot as plt
 
-"""Given a GeneID, construct the histogram of read counts per cell."""
-
 
 def plot_read_counts(
-    dir_path: Union[str, Path] = None,
-    gene_id: str = None
-) -> bool:
+    dir_path: Union[str, Path],
+    gene_id: str
+) -> str:
     """Plots histogram of gene ID and read counts from .csv files.
 
-        This function reads .csv files from a directory formatted
+    This function reads .csv files from a directory formatted
     "GeneID, Counts" and plots a histogram of read counts for a
     chosen geneID.
 
@@ -23,96 +23,126 @@ def plot_read_counts(
         dir_path: Path of directory containing .csv files of read counts.
         gene_id: Name of gene to plot.
 
+    Returns:
+        String representing path to .svg plot file.
+
     Raises:
-        ValueError: No value is passed for path and/or gene ID.
         ValueError: Path passed in does not exist.
-        ValueError: Gene not found in selection of .csv files.
         TypeError: Gene ID parameter passed is not a String.
-        AttributeError: No .csv files in chosen directory
+        FileNotFoundError: File path does not contain any .csv files.
+        KeyError: A file containing an entry of the chosen gene is missing
+                  a count entry for it.
+        TypeError: A file containing an entry of the chosen gene has a count
+                   that is not a number.
     """
+    LOGGER = logging.getLogger(__name__)
+
+    dir_path = Path(dir_path)
+
+    if not dir_path.exists():
+        raise ValueError("Invalid Path")
+
+    if not isinstance(gene_id, str):
+        raise TypeError("Invalid gene ID")
+
+    # identify csv files from directory, formatted ['Gene', 'Count']
+    # if this is not immediately cast as list, on some python versions
+    # it sets file_paths to null after a single call
+    file_paths = list(dir_path.glob("*.csv"))
+    file_paths.sort()
+
+    if len(file_paths) == 0:
+        raise FileNotFoundError("No .csv files found in chosen directory")
+
+    gene_count_dict = {}
+    file_counter = 0
+
+    LOGGER.info("Running with %s and gene %s" % (dir_path, gene_id))
+
+    for file_path in file_paths:
+        # read in csv here via pandas
+        df_read_counts = pandas.read_csv(str(file_path),
+                                         header=None, names=['Gene', 'Count'])
+
+        # confirm that gene entry exists for edge case where count may be deleted
+        confirm_gene_presence = df_read_counts.loc[df_read_counts.Gene == gene_id,
+                                                   'Gene'].tolist()
+
+        # find gene_id within dataframe
+        gene_count = df_read_counts.loc[df_read_counts.Gene == gene_id,
+                                        'Count'].tolist()
+
+        # # If an entry exists for the gene, but the count is missing, a KeyError is thrown
+        if confirm_gene_presence and not gene_count:
+            raise KeyError("%s.csv contains an entry for %s, but is "
+                           "missing a count." % (file_path.stem, gene_id))
+
+        # If an entry exists for the gene, but the count is not a number, a TypeError is thrown
+        if confirm_gene_presence:
+            try:
+                for i, count in enumerate(gene_count):
+                    gene_count[i] = int(count)
+
+            except ValueError:
+                raise TypeError("%s.csv contains an entry for %s, but is "
+                                "not a number." % (file_path.stem, gene_id))
+
+        if not gene_count:
+            LOGGER.warning(f"File {file_path.stem}.csv does not contain an entry for {gene_id}, "
+                           "this is interpreted as 0")
+            gene_count = [0]
+
+        if len(gene_count) > 1:
+            LOGGER.warning(
+                "%s.csv contains more than one entry for chosen gene - these will be summed"
+                % (file_path.stem)
+            )
+
+        file_counter += 1
+        # Uncomment to use file name as label -> does not autoscale pyplot
+        # gene_count_dict[file_path.stem] = sum(gene_count)
+        gene_count_dict[f"Read {file_counter}"] = sum(gene_count)
+
+    LOGGER.info('Read complete from %s files' % (file_counter))
+
+    # read in dictionary from read_counts and plot counts on the same histogram
+    file_names = list(gene_count_dict.keys())
+    counts = list(gene_count_dict.values())
+
+    # create and show bar plot of read counts for chosen gene
+    plt.bar(range(len(gene_count_dict)), counts, tick_label=file_names, width=0.4)
+    plt.title('Counts for %s' % (gene_id))
+    plt.autoscale(axis='both')
+    plot_file_path = Path(f"{Path.cwd()}/plots/{get_file_name()}.svg")
+    plt.savefig(plot_file_path)
+    LOGGER.info(f"Plot successfully generated and saved at {plot_file_path}")
+
+    return(plot_file_path)
+
+
+def get_file_name() -> str:
+    """Helper function to determine output filename."""
+    datetime_str = datetime.now().strftime("%y%m%d")
+    file_name_index = 1
+    plot_file_name = f"reads_plot_{datetime_str}_{file_name_index}"
+    # while(Path.exists(Path(f"{Path.cwd()}/plots/{plot_file_name}"))):
+    #     file_name_index += 1
+    # plot_file_name = f"reads_plot_{datetime_str}_{file_name_index}"
+    return plot_file_name
+
+
+def main():
+    """Prompts user in cl to enter path and gene to plot."""
     # Initialize logger
     logging.basicConfig(
         format='[%(asctime)s: %(levelname)s] "%(module)s" %(message)s',
         level=logging.INFO)
-    LOGGER = logging.getLogger(__name__)
 
-    try:
-        dir_path = Path(dir_path)
-
-        if not dir_path.exists():
-            LOGGER.critical("Invalid path")
-            raise ValueError("Invalid Path")
-
-        elif not isinstance(gene_id, str):
-            LOGGER.critical("Invalid gene ID, please enter as string")
-            raise TypeError("Invalid gene ID")
-
-        # identify csv files from directory, formatted ['Gene', 'Count']
-        # if this is not immediately cast as list, on some python versions
-        # it sets file_paths to null after a single call which is big sad
-        file_paths = list(dir_path.glob("*.csv"))
-        file_paths.sort()
-
-        if file_paths == 0:
-            LOGGER.warning('No csv files found in current directory, exiting')
-            raise AttributeError("No .csv files found in chosen directory")
-
-        gene_count_dict = {}
-        file_counter = 1
-
-        LOGGER.info("Run with %s and gene %s" % (dir_path, gene_id))
-
-        for file_path in file_paths:
-            # read in csv here and transform to pandas dataframe
-            df_read_counts = pandas.read_csv(str(file_path),
-                                             header=None, names=['Gene', 'Count'])
-
-            # find gene_id within dataframe
-            gene_count = df_read_counts.loc[df_read_counts.Gene == gene_id,
-                                            'Count'].tolist()
-
-            if len(gene_count) > 1:
-                LOGGER.warning(
-                    "%s.csv contains more than one entry for chosen gene - these will be summed"
-                    % (file_path.stem)
-                )
-
-            elif not gene_count:
-                LOGGER.warning(
-                    "%s.csv does not contain read of chosen gene, this is interpreted as 0"
-                    % (file_path.stem))
-                gene_count = [0]
-
-            # in case count entry is missing, interpreted as 0
-            if not gene_count:
-                gene_count = [0]
-                LOGGER.warning(
-                    "File %s contains an entry for this gene but is missing a count number \
-                        this is interpreted as 0" % (file_path.stem)
-                )
-
-            file_counter += 1
-            gene_count_dict[file_path.stem] = sum(gene_count)
-
-    except AttributeError:
-        LOGGER.fatal("Invalid selection, please verify input")
-        raise ValueError("Either the path, gene ID, or both were not properly specified")
-
-    if sum(gene_count_dict.values()) == 0:
-        LOGGER.warning(
-            "Gene not found -> Please check for correct spelling or ID"
-        )
-        raise ValueError("Gene not found")
-
-    else:
-        LOGGER.info('Read complete from %s files' % (file_counter-1))
-
-        # read in dictionary from read_counts and plot counts on the same histogram
-        file_names = list(gene_count_dict.keys())
-        counts = list(gene_count_dict.values())
-
-        # create and show bar plot of read counts for chosen gene
-        plt.bar(range(len(gene_count_dict)), counts, tick_label=file_names)
-        plt.title('Counts for %s' % (gene_id))
-        plt.show()
-        return True
+    # Prompt user for input
+    csv_path = input("\nPlease enter a path: ")
+    gene_of_interest = input("\nPlease enter a gene name to plot: ")
+    plot_read_counts(csv_path, gene_of_interest)
+
+
+if __name__ == "__main__":
+    main()

tests/resources/Transcript4.csv

-GENE1,629
-GENE2,803
-GENE3,106
-GENE4,378
-GENE5,728
-GENE6,783
-GENE7,353
-GENE8,747
-GENE9,253
-GENE10,883
-GENE11,552
-GENE12,655
-GENE13,309
-GENE14,133
-GENE15,131
-GENE16,626
-GENE17,669
-GENE18,493
-GENE19,304

tests/resources/Transcript5.csv

-GENE1,830
-GENE2,602
-GENE3,859
-GENE4,174
-GENE5,525
-GENE6,606
-GENE7,851
-GENE8,910
-GENE9,194
-GENE10,415
-GENE11,953
-GENE12,299
-GENE13,127
-GENE14,750
-GENE15,968
-GENE16,282
-GENE17,868
-GENE18,688
-GENE19,650

tests/resources/Transcript6.csv

-GENE1,676
-GENE2,787
-GENE3,876
-GENE4,368
-GENE5,676
-GENE6,896
-GENE7,865
-GENE8,585
-GENE9,853
-GENE10,447
-GENE11,583
-GENE12,573
-GENE13,895
-GENE14,207
-GENE15,562
-GENE16,411
-GENE17,635
-GENE18,469
-GENE19,128

tests/resources/Transcript7negctrl.csv

-Random,Data,for
-This,is,a
-negative,control,test
-some,numbers,
-234,,
-,432,
-,,
-32,,

tests/resources/Transcript_read_counts_invalid.csv

+Improper,Data
+GENE6,nan

tests/resources/Transcript3.csv → tests/resources/Transcript_read_counts_missing-gene7.csv

@@ -4,7 +4,7 @@ GENE3,859
 GENE4,174
 GENE5,525
 GENE6,606
-,
+GENE7,
 GENE8,910
 GENE9,194
 GENE10,415

tests/resources/Transcript1.csv → tests/resources/Transcript_read_counts_valid.csv

-GENE1,92
-GENE2,13
-GENE3,73
-GENE4,83
-GENE5,32
-GENE6,136
+GENE1,92
+GENE2,13
+GENE3,73
+GENE4,83
+GENE5,32
+GENE6,136
 GENE7,36
\ No newline at end of file

tests/test_plot_read_counts.py

@@ -12,11 +12,10 @@ class TestPlotReadCounts ():
         "dir_path, gene_id, expected",
         [
             ('a', 'GENE1', ValueError),
-            ('Path.home()', 5, TypeError),
-            (None, None, ValueError),
-            ('Path.home()', 'GENE1', AttributeError),
-            (Path(str(Path.parent())+"/tests/resources/"), 'GENE25', ValueError),
-
+            (Path(f"{Path.cwd()}/tests/"), 'GENE1', FileNotFoundError),
+            (Path(f"{Path.cwd()}/tests/resources/"), 5, TypeError),
+            (Path(f"{Path.cwd()}/tests/resources/"), 'GENE6', TypeError),
+            (Path(f"{Path.cwd()}/tests/resources/"), 'GENE7', TypeError),
         ]
     )
     def test_invalid_input(self, dir_path, gene_id, expected):
@@ -25,13 +24,13 @@ class TestPlotReadCounts ():
             plot_read_counts(dir_path, gene_id)
 
     @pytest.mark.parametrize(
-        "dir_path, gene_id, expected",
+        "dir_path, gene_id",
         [
-            (Path(str(Path.parent())+"/tests/resources/"), 'GENE1', True),
-            (Path(str(Path.parent())+"/tests/resources/"), 'GENE1', True),
-            (Path(str(Path.parent())+"/tests/resources/"), 'GENE7', True),
+            (Path(f"{Path.cwd()}/tests/resources/"), 'GENE1'),
+            (Path(f"{Path.cwd()}/tests/resources/"), 'GENE2'),
+            (Path(f"{Path.cwd()}/tests/resources/"), 'GENE3'),
         ]
     )
-    def validate_input(self, dir_path, gene_id):
+    def test_valid_input(self, dir_path, gene_id):
         """Tests valid input with return value boolean."""
-        assert plot_read_counts(dir_path, gene_id) is True
+        assert Path.exists(plot_read_counts(dir_path, gene_id))