ss-development: separated out

.github/workflows/discord_pca_analysis.yml

@@ -0,0 +1,31 @@
+name: PRINCIPAL COMPONENT ANALYSIS BOT
+
+on: [ workflow_dispatch ]
+
+jobs:
+  test:
+    runs-on: "ubuntu-latest"
+    steps:
+      - name: Checkout source
+        uses: actions/checkout@v2
+
+      - name: Setup python
+        uses: actions/setup-python@v2
+        with:
+          python-version: 3.9
+          architecture: x64
+      - name: Install
+        run: |
+          pip install pandas
+          pip install click
+          pip install sklearn
+          pip install numpy
+          pip install rdkit-pypi
+          pip install bokeh
+      - name: Run Checker
+        env:
+          GITHUB_TOKEN: ${{ secrets.PCA_BOT_TOKEN }}
+        run: |
+          cd bot_services/discord
+          python principal_component_analysis.py
+#          python principal_component_analysis.py --smiles_list --morgan_radius --bit_representation --number_of_clusters --number_of_components --random_state --file_name --principal_component_x --principal_component_y --x_axis_label --y_axis_label --plot_width --plot_height --title,

global_chem/convert_to_rdf.py

@@ -0,0 +1,43 @@
+import rdflib
+import csv
+import pandas as pd
+
+if __name__ == '__main__':
+
+    df = pd.read_csv('/Users/sulimansharif/projects/global-chem/global_chem/global_chem.tsv', delimiter='\t', header=None, names=['name', 'smiles', 'node', 'predicate', 'path'])
+
+    # Create the graph object which holds the triples
+    graph = rdflib.Graph()
+
+    for i, row in df.iterrows():
+        s = rdflib.URIRef(f'#/{row["name"]}')
+        p = rdflib.URIRef("#connectsTo")
+        o = rdflib.URIRef(f'#/{row["node"]}')
+        graph.add((s, p, o))
+
+    for i, row in df.iterrows():
+
+      predicate = row['predicate']
+
+      if str(predicate) == 'nan':
+         predicate = 'miscellaenous'
+
+      s = rdflib.URIRef(f'#/{row["node"]}')
+      p = rdflib.URIRef("#connectsTo")
+      o = rdflib.URIRef(f'#/{predicate}')
+      graph.add((s, p, o))
+
+    for i, row in df.iterrows():
+
+      predicate = row['predicate']
+
+      if str(predicate) == 'nan':
+        predicate = 'miscellaenous'
+
+      s = rdflib.URIRef(f'#/{predicate}')
+      p = rdflib.URIRef("#connectsTo")
+      o = rdflib.URIRef(f'#/{"global-chem"}')
+
+      graph.add((s, p, o))
+
+    graph.serialize(destination='graph.ttl', format='application/rdf+xml')