fixed typos

7caba48a · Laura Urbanska · 2c662762 · 7caba48a · 7caba48a
Commit 7caba48a authored 2 years ago by Laura Urbanska
--- a/scripts/match_reprtranscript_expressionlevel.py
+++ b/scripts/match_reprtranscript_expressionlevel.py
@@ -2,7 +2,7 @@
 import pandas as pd
 import json
 import re
-import rerpresentative_v4 as repr
+import representative as repr
 import os


@@ -197,4 +197,4 @@ print("this is the function :\n\n {}".format(match_final))

 if __name__ == "__main__":  
    match_reprTranscript_expressionLevel()
- 
\ No newline at end of file
+ 
--- a/scripts/new_exe_file.ipynb
+++ b/scripts/new_exe_file.ipynb
@@ -2,50 +2,31 @@
 "cells": [
  {
   "cell_type": "code",
-   "execution_count": 9,
+   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
-     "name": "stderr",
-     "output_type": "stream",
-     "text": [
-      "usage: ipykernel_launcher.py [-h] --annotation ANNOTATION --expression_level\n",
-      "                             EXPRESSION_LEVEL --output_csv OUTPUT_CSV\n",
-      "                             --output_gtf OUTPUT_GTF --transcript_number\n",
-      "                             TRANSCRIPT_NUMBER\n",
-      "ipykernel_launcher.py: error: the following arguments are required: --annotation, --expression_level, --output_csv, --output_gtf, --transcript_number\n"
-     ]
-    },
-    {
-     "ename": "SystemExit",
-     "evalue": "2",
+     "ename": "ModuleNotFoundError",
+     "evalue": "No module named 'rerpresentative_v4'",
     "output_type": "error",
     "traceback": [
-      "An exception has occurred, use %tb to see the full traceback.\n",
-      "\u001b[0;31mSystemExit\u001b[0m\u001b[0;31m:\u001b[0m 2\n"
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m                       Traceback (most recent call last)",
+      "\u001b[1;32m/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb Cell 1\u001b[0m in \u001b[0;36m<cell line: 7>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=4'>5</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mpoisson_sampling\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mps\u001b[39;00m\n\u001b[1;32m      <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=5'>6</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mwritegtf\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mgt\u001b[39;00m\n\u001b[0;32m----> <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=6'>7</a>\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mmatch_reprtranscript_expressionlevel\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mma\u001b[39;00m\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=9'>10</a>\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mexe\u001b[39m(input_file, csv, gtf, transcript_nr):\n\u001b[1;32m     <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=10'>11</a>\u001b[0m     file_name,source_pathway_name_2,deposit_pathway_name_2 \u001b[39m=\u001b[39m te\u001b[39m.\u001b[39mextract_transcript(input_file, deposit_pathway_name \u001b[39m=\u001b[39m \u001b[39mTrue\u001b[39;00m, Input_free \u001b[39m=\u001b[39m Input_free)\n",
+      "File \u001b[0;32m~/code/transcript-sampler/scripts/match_reprtranscript_expressionlevel.py:5\u001b[0m, in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mjson\u001b[39;00m\n\u001b[1;32m      4\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mre\u001b[39;00m\n\u001b[0;32m----> 5\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mrerpresentative_v4\u001b[39;00m \u001b[39mas\u001b[39;00m \u001b[39mrepr\u001b[39;00m\n\u001b[1;32m      6\u001b[0m \u001b[39mimport\u001b[39;00m \u001b[39mos\u001b[39;00m\n\u001b[1;32m      9\u001b[0m \u001b[39mdef\u001b[39;00m \u001b[39mdict_reprTrans_to_df\u001b[39m(dict_reprTrans: \u001b[39mdict\u001b[39m):\n",
+      "\u001b[0;31mModuleNotFoundError\u001b[0m: No module named 'rerpresentative_v4'"
     ]
    }
   ],
   "source": [
-    "import os\n",
-    "\n",
    "import argparse\n",
    "import transcript_extractor as te\n",
    "import exon_length_filter as elf\n",
    "import representative as rtcl\n",
-    "import representative as rp\n",
+    "import poisson_sampling as ps\n",
+    "import writegtf as gt\n",
+    "import match_reprtranscript_expressionlevel as ma\n",
    "\n",
-    "if __name__ == '__main__':\n",
-    "    parser = argparse.ArgumentParser(\n",
-    "        description=\"transcript sampler\",\n",
-    "        formatter_class=argparse.ArgumentDefaultsHelpFormatter\n",
-    "    )\n",
-    "    parser.add_argument(\"--annotation\", required=True, help=\"gtf file with genome annotation\")\n",
-    "    #parser.add_argument(\"--expression_level\", required=True, help=\"csv file with expression level\")\n",
-    "    parser.add_argument(\"--output_csv\", required=True, help=\"output csv file\")\n",
-    "    parser.add_argument(\"--output_gtf\", required=True, help=\"output gtf file\")\n",
-    "    parser.add_argument(\"--transcript_number\", required=True, help=\"total number of transcripts to sample\")\n",
-    "    args = parser.parse_args()\n",
    "\n",
    "def exe(input_file, csv, gtf, transcript_nr):\n",
    "    file_name,source_pathway_name_2,deposit_pathway_name_2 = te.extract_transcript(input_file, deposit_pathway_name = True, Input_free = Input_free)\n",
@@ -58,6 +39,27 @@
    "    print(\"Transcripts filtered\\n\")\n",
    "    elf.exon_length_filter(file_name,gen_dict= pre_filter_representative_transcripts_dict, Input_free = True)\n",
    "\n",
+    "    tsv_input = ma.output_tsv()\n",
+    "    print(\"Poisson sampling of transcripts\")\n",
+    "    ps.transcript_sampling(transcript_nr, tsv_input, csv)\n",
+    "    print(\"output csv file ready\")\n",
+    "    \n",
+    "    print(\"writing output gtf file\")\n",
+    "    gt.gtf_file_writer(input_file, csv, gtf)\n",
+    "\n",
+    "\n",
+    "\n",
+    "if __name__ == '__main__':\n",
+    "    parser = argparse.ArgumentParser(\n",
+    "        description=\"transcript sampler\",\n",
+    "        formatter_class=argparse.ArgumentDefaultsHelpFormatter\n",
+    "    )\n",
+    "    parser.add_argument(\"--annotation\", required=True, help=\"gtf file with genome annotation\")\n",
+    "    parser.add_argument(\"--output_csv\", required=True, help=\"output csv file\")\n",
+    "    parser.add_argument(\"--output_gtf\", required=True, help=\"output gtf file\")\n",
+    "    parser.add_argument(\"--transcript_number\", required=True, help=\"total number of transcripts to sample\")\n",
+    "    args = parser.parse_args()\n",
+    "    exe(args.annotation, args.output_csv, args.output_gtf, args.transcript_nr)\n",
    "\n",
    "    #return(file_name,source_pathway_name,deposit_pathway_name)\n",
    "\n"

 %% Cell type:code id: tags:

 ``` python
-import os
-
 import argparse
 import transcript_extractor as te
 import exon_length_filter as elf
 import representative as rtcl
-import representative as rp
+import poisson_sampling as ps
+import writegtf as gt
+import match_reprtranscript_expressionlevel as ma

-if __name__ == '__main__':
-    parser = argparse.ArgumentParser(
-        description="transcript sampler",
-        formatter_class=argparse.ArgumentDefaultsHelpFormatter
-    )
-    parser.add_argument("--annotation", required=True, help="gtf file with genome annotation")
-    #parser.add_argument("--expression_level", required=True, help="csv file with expression level")
-    parser.add_argument("--output_csv", required=True, help="output csv file")
-    parser.add_argument("--output_gtf", required=True, help="output gtf file")
-    parser.add_argument("--transcript_number", required=True, help="total number of transcripts to sample")
-    args = parser.parse_args()

 def exe(input_file, csv, gtf, transcript_nr):
    file_name,source_pathway_name_2,deposit_pathway_name_2 = te.extract_transcript(input_file, deposit_pathway_name = True, Input_free = Input_free)
    inter_mediate_file_directory = input_file +"_intermediate_file.txt"

    print("Transcripts are filtered based on transcript score. Please wait...")

    pre_filter_representative_transcripts_dict = rtcl.find_repr_by_SupportLevel(inter_mediate_file_directory)

    print("Transcripts filtered\n")
    elf.exon_length_filter(file_name,gen_dict= pre_filter_representative_transcripts_dict, Input_free = True)

+    tsv_input = ma.output_tsv()
+    print("Poisson sampling of transcripts")
+    ps.transcript_sampling(transcript_nr, tsv_input, csv)
+    print("output csv file ready")
+
+    print("writing output gtf file")
+    gt.gtf_file_writer(input_file, csv, gtf)
+
+
+
+if __name__ == '__main__':
+    parser = argparse.ArgumentParser(
+        description="transcript sampler",
+        formatter_class=argparse.ArgumentDefaultsHelpFormatter
+    )
+    parser.add_argument("--annotation", required=True, help="gtf file with genome annotation")
+    parser.add_argument("--output_csv", required=True, help="output csv file")
+    parser.add_argument("--output_gtf", required=True, help="output gtf file")
+    parser.add_argument("--transcript_number", required=True, help="total number of transcripts to sample")
+    args = parser.parse_args()
+    exe(args.annotation, args.output_csv, args.output_gtf, args.transcript_nr)

    #return(file_name,source_pathway_name,deposit_pathway_name)

 ```

 %% Output

-    usage: ipykernel_launcher.py [-h] --annotation ANNOTATION --expression_level
-                                 EXPRESSION_LEVEL --output_csv OUTPUT_CSV
-                                 --output_gtf OUTPUT_GTF --transcript_number
-                                 TRANSCRIPT_NUMBER
-    ipykernel_launcher.py: error: the following arguments are required: --annotation, --expression_level, --output_csv, --output_gtf, --transcript_number
-
-An exception has occurred, use %tb to see the full traceback.
-    SystemExit: 2
+    ---------------------------------------------------------------------------
+    ModuleNotFoundError                       Traceback (most recent call last)
+    /home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb Cell 1 in <cell line: 7>()
+          <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=4'>5</a> import poisson_sampling as ps
+          <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=5'>6</a> import writegtf as gt
+    ----> <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=6'>7</a> import match_reprtranscript_expressionlevel as ma
+         <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=9'>10</a> def exe(input_file, csv, gtf, transcript_nr):
+         <a href='vscode-notebook-cell:/home/laura/code/transcript-sampler/scripts/new_exe_file.ipynb#W1sZmlsZQ%3D%3D?line=10'>11</a>     file_name,source_pathway_name_2,deposit_pathway_name_2 = te.extract_transcript(input_file, deposit_pathway_name = True, Input_free = Input_free)
+File     ~/code/transcript-sampler/scripts/match_reprtranscript_expressionlevel.py:5, in <module>
+          3 import json
+          4 import re
+    ----> 5 import rerpresentative_v4 as repr
+          6 import os
+          9 def dict_reprTrans_to_df(dict_reprTrans: dict):
+    ModuleNotFoundError: No module named 'rerpresentative_v4'

 %% Cell type:code id: tags:

 ``` python
 ```