output time and make compression mtime=0

broadinstitute · Jun 21, 2021 · 2de5827 · 2de5827
1 parent 26a511d
commit 2de5827
Show file tree

Hide file tree

Showing 3 changed files with 10 additions and 8 deletions.
diff --git a/perturbation-count-summary.ipynb b/perturbation-count-summary.ipynb
@@ -64,15 +64,15 @@
       "There are a total of 52,223 image-based profiles assayed in 2016_04_01_a549_48hr_batch1\n",
       "There are a total of 10,752 image-based consensus profiles assayed in 2016_04_01_a549_48hr_batch1\n",
       "There are 1,571 unique compounds assayed in 2016_04_01_a549_48hr_batch1\n",
-      "There are 1 unique time points assayed in 2016_04_01_a549_48hr_batch1\n",
+      "There are 1 unique time points assayed in 2016_04_01_a549_48hr_batch1 (['48H'])\n",
       "There are 7 unique doses assayed in 2016_04_01_a549_48hr_batch1\n",
       "There are 1 unique cell lines assayed in 2016_04_01_a549_48hr_batch1 (['A549'])\n",
       "There is a total of 9,395 unique perturbations assayed in 2016_04_01_a549_48hr_batch1\n",
       "\n",
       "There are a total of 51,447 image-based profiles assayed in 2017_12_05_Batch2\n",
       "There are a total of 10,368 image-based consensus profiles assayed in 2017_12_05_Batch2\n",
       "There are 349 unique compounds assayed in 2017_12_05_Batch2\n",
-      "There are 3 unique time points assayed in 2017_12_05_Batch2\n",
+      "There are 3 unique time points assayed in 2017_12_05_Batch2 (['24H' '48H' '6H'])\n",
       "There are 6 unique doses assayed in 2017_12_05_Batch2\n",
       "There are 3 unique cell lines assayed in 2017_12_05_Batch2 (['A549' 'MCF7' 'U2OS'])\n",
       "There is a total of 9,369 unique perturbations assayed in 2017_12_05_Batch2\n",
@@ -94,8 +94,8 @@
     "    num_compounds = len(consensus_df.Metadata_broad_sample.unique())\n",
     "    print(f\"There are {num_compounds:,} unique compounds assayed in {batch}\")\n",
     "    \n",
-    "    time_points = len(consensus_df.Metadata_time_point.unique())\n",
-    "    print(f\"There are {time_points} unique time points assayed in {batch}\")\n",
+    "    time_points = consensus_df.Metadata_time_point.unique()\n",
+    "    print(f\"There are {len(time_points)} unique time points assayed in {batch} ({time_points})\")\n",
     "    \n",
     "    doses = len(consensus_df.Metadata_dose_recode.unique())\n",
     "    print(f\"There are {doses} unique doses assayed in {batch}\")\n",
@@ -197,8 +197,10 @@
     "    print(f\"In batch {batch}, we profiled {batch_cell_count:,} cells\")\n",
     "    \n",
     "    output_cell_count_summary_file = cell_count_dir / f\"{batch}_metadata_cell_count_summary.tsv.gz\"\n",
-    "    batch_metadata_df.to_csv(output_cell_count_summary_file, index=False)\n",
-    "    \n",
+    "    batch_metadata_df.to_csv(\n",
+    "        output_cell_count_summary_file, index=False, compression={\"method\": \"gzip\", \"mtime\": 0}\n",
+    "    )\n",
+    "        \n",
     "    total_cells += batch_cell_count\n",
     "    \n",
     "print(f\"\\nWe profiled a total of {total_cells:,} cells in the LINCS Cell Painting dataset\")"

diff --git a/profiles/cell_count/2016_04_01_a549_48hr_batch1_metadata_cell_count_summary.tsv.gz b/profiles/cell_count/2016_04_01_a549_48hr_batch1_metadata_cell_count_summary.tsv.gz
diff --git a/profiles/cell_count/2017_12_05_Batch2_metadata_cell_count_summary.tsv.gz b/profiles/cell_count/2017_12_05_Batch2_metadata_cell_count_summary.tsv.gz