Creation script

Pyrazinamide/alpha polymorph_volume.csv

@@ -0,0 +1,3 @@
+PYRZIN
+Identifier, Property              , Value (Angstrom^3),          Std,   N,    Name,    Reference    ,                 Comment
+1, Unit Cell Volume @  Unknown, 568.67, 1.15, 2,    ,    10.1107/S0365110X60001680, generated by automatic script, add Name and double check temperature etc.

Pyrazinamide/beta polymorph_volume.csv

@@ -0,0 +1,3 @@
+PYRZIN01
+Identifier, Property              , Value (Angstrom^3),          Std,   N,    Name,    Reference    ,                 Comment
+1, Unit Cell Volume @  Unknown, 559.73, 0.00, 1,    ,    10.1107/S0567740872003589, generated by automatic script, add Name and double check temperature etc.

Pyrazinamide/delta polymorph_volume.csv

@@ -0,0 +1,3 @@
+PYRZIN02
+Identifier, Property              , Value (Angstrom^3),          Std,   N,    Name,    Reference    ,                 Comment
+1, Unit Cell Volume @  Unknown, 279.56, 0.00, 1,    ,    10.1107/S0567740872004856, generated by automatic script, add Name and double check temperature etc.

Pyrazinamide/gamma polymorph_volume.csv

@@ -0,0 +1,3 @@
+PYRZIN03
+Identifier, Property              , Value (Angstrom^3),          Std,   N,    Name,    Reference    ,                 Comment
+1, Unit Cell Volume @  Unknown, 277.59, 2.45, 2,    ,    10.1107/S0365110X61002102, generated by automatic script, add Name and double check temperature etc.

existing_CSD_data.py

@@ -0,0 +1,56 @@
+import ccdc
+import sys
+import os
+import numpy as np
+
+entries = ccdc.io.EntryReader('CSD')
+family = sys.argv[1]
+common_name = sys.argv[2]
+Polymorphs = []
+volumes_by_polymorph = {}
+temperature_by_polymorph = {}
+Refcode_by_polymorph = {}
+dois_by_polymorph = {}
+for i in range(9):
+    if i == 0:
+        num = ""
+    else:
+        num = "%02i" % i
+    full_name = f"{family}{num}"
+    print(full_name)
+    try:
+        entry = entries.entry(full_name)
+    except Exception as e:
+        print(f"Could not retrieve crystal for {full_name}: {e}")
+        break
+    polymorph = entry.polymorph if entry.polymorph else "Unknown"
+    volume = entry.crystal.cell_volume
+    if volume is not None:
+        if polymorph not in volumes_by_polymorph:
+            volumes_by_polymorph[polymorph] = []
+        volumes_by_polymorph[polymorph].append(volume)
+    temperature = entry.temperature if entry.temperature else "Unknown"
+    if temperature is not None:
+        if polymorph not in temperature_by_polymorph:
+            temperature_by_polymorph[polymorph] = []
+        temperature_by_polymorph[polymorph].append(temperature)
+    refcode = entry.identifier
+    if polymorph not in Refcode_by_polymorph:
+        Refcode_by_polymorph[polymorph] = []
+    Refcode_by_polymorph[polymorph].append(refcode)
+    doi = entry.publication.doi if entry.publication and entry.publication.doi else "Unknown"
+    if polymorph not in dois_by_polymorph:
+        dois_by_polymorph[polymorph] = []
+    dois_by_polymorph[polymorph].append(doi)
+if os.path.exists(common_name):
+    print(f"folder {common_name} exists.")
+else:
+    print(f"making folder {common_name}")
+    os.mkdir(common_name)
+
+for polymorph, volumes in volumes_by_polymorph.items():
+    output_file = open(os.path.join(common_name, f"{polymorph}_volume.csv"), 'w')
+    output_file.write("%s\n" % (Refcode_by_polymorph[polymorph][0]))  # should be best R factor refcode rather than first really
+    output_file.write("Identifier, Property              , Value (Angstrom^3),          Std,   N,    Name,    Reference    ,                 Comment\n")
+    output_file.write(f"1, Unit Cell Volume @  {temperature_by_polymorph[polymorph][0]}, {np.mean(volumes):.2f}, {np.std(volumes):.2f}, {len(volumes)},    ,{dois_by_polymorph[polymorph][0]}, generated by automatic script; add Name and double check temperature etc.\n")
+