[Response to Reviewers] Update dimensionality reduction figures (#67)

* fix argument and path

* move faceted UMAP to panel A

* update supplementary umap after updating umap in fig2

* add tsne figure notebooks

* add notebook for applying tsne

* fix typo and rerun notebook

* respond to reviewer comments

* remove unused variables and make tsv

1.split_data/explore_data.ipynb

@@ -69,7 +69,9 @@
     "# Set constants\n",
     "feature_spaces = [\"CP\", \"DP\", \"CP_and_DP\"]\n",
     "\n",
-    "output_dir = \"data\"\n",
+    "output_dir = pathlib.Path(\"data\")\n",
+    "output_dir.mkdir(exist_ok=True)\n",
+    "\n",
     "output_basename = pathlib.Path(output_dir, \"pairwise_correlations\")"
    ]
   },
@@ -270,7 +272,7 @@
    "source": [
     "for feature_space in feature_spaces:\n",
     "    # Get specific feature sets\n",
-    "    cp_feature_df, cp_label_df = get_X_y_data(labeled_data, dataset=feature_space)\n",
+    "    cp_feature_df, cp_label_df = get_X_y_data(labeled_data, feature_type=feature_space)\n",
     "\n",
     "    # Calculate pairwise correlations between nuclei\n",
     "    cp_tidy_corr_df = create_tidy_corr_matrix(cp_feature_df, cp_label_df)\n",
@@ -283,9 +285,9 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "Python [conda env:phenotypic_profiling]",
    "language": "python",
-   "name": "python3"
+   "name": "conda-env-phenotypic_profiling-py"
   },
   "language_info": {
    "codemirror_mode": {
@@ -297,7 +299,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.18"
+   "version": "3.9.19"
   }
  },
  "nbformat": 4,

1.split_data/scripts/nbconverted/explore_data.py

@@ -52,7 +52,9 @@ def create_tidy_corr_matrix(data_array, labels):
 # Set constants
 feature_spaces = ["CP", "DP", "CP_and_DP"]
 
-output_dir = "data"
+output_dir = pathlib.Path("data")
+output_dir.mkdir(exist_ok=True)
+
 output_basename = pathlib.Path(output_dir, "pairwise_correlations")
 
 
@@ -72,7 +74,7 @@ def create_tidy_corr_matrix(data_array, labels):
 
 for feature_space in feature_spaces:
     # Get specific feature sets
-    cp_feature_df, cp_label_df = get_X_y_data(labeled_data, dataset=feature_space)
+    cp_feature_df, cp_label_df = get_X_y_data(labeled_data, feature_type=feature_space)
 
     # Calculate pairwise correlations between nuclei
     cp_tidy_corr_df = create_tidy_corr_matrix(cp_feature_df, cp_label_df)