Initial commit

app.py

@@ -0,0 +1,221 @@
+#!/usr/bin/env python
+# coding: utf-8
+
+# In[1]:
+
+import numpy as np
+import pandas as pd
+import regex as re
+import streamlit as st
+
+
+# In[2]:
+
+cobie_file = pd.ExcelFile(path_to_cobie_file)
+
+cobie_floor_df = cobie_file.parse(sheet_name = 'Floor', dtype={'ExtIdentifier':str, 'Name':str})
+cobie_space_df = cobie_file.parse(sheet_name = 'Space', dtype={'ExtIdentifier':str, 'Name':str})
+cobie_type_df = cobie_file.parse(sheet_name = 'Type', dtype={'ExtIdentifier':str, 'Description':str, 'Name':str})
+cobie_system_df = cobie_file.parse(sheet_name = 'System', dtype={'ExtIdentifier':str, 'Description':str, 'Name':str})
+cobie_component_df = cobie_file.parse(sheet_name = 'Component', dtype={'ExtIdentifier':str, 'Space':str, 'Description':str, 'Name':str})
+
+
+def decodeIfc(txt):
+    # In regex "\" is hard to manage in Python... I use this workaround
+    txt = txt.replace('\\', 'µµµ')
+    txt = re.sub('µµµX2µµµ([0-9A-F]{4,})+µµµX0µµµ', decodeIfcX2, txt)
+    txt = re.sub('µµµSµµµ(.)', decodeIfcS, txt)
+    txt = re.sub('µµµXµµµ([0-9A-F]{2})', decodeIfcX, txt)
+    txt = txt.replace('µµµ','\\')
+    return txt
+
+def decodeIfcX2(match):
+    # X2 encodes characters with multiple of 4 hexadecimal numbers.
+    return ''.join(list(map(lambda x : chr(int(x,16)), re.findall('([0-9A-F]{4})',match.group(1)))))
+
+def decodeIfcS(match):
+    return chr(ord(match.group(1))+128)
+
+def decodeIfcX(match):
+    # Sometimes, IFC files were made with old Mac... wich use MacRoman encoding.
+    num = int(match.group(1), 16)
+    if (num <= 127) | (num >= 160):
+        return chr(num)
+    else:
+        return bytes.fromhex(match.group(1)).decode("macroman")
+
+def convert_unicode_string(row, column_name):
+    return decodeIfc(row[column_name])
+
+
+columns_to_decode = ['Name', 'TypeName', 'Description']    
+for column_to_decode in columns_to_decode:
+    
+    cobie_flat[column_to_decode] = cobie_flat.apply(
+        convert_unicode_string,
+        column_name=column_to_decode,
+        axis=1
+    )
+
+
+# In[3]:
+
+cobie_type_df.rename(columns={
+    'Name':'TypeName',
+    'ExtObject':'TypeExtObject',
+    'ExtIdentifier':'TypeExtIdentifier',
+}, inplace=True)
+
+cobie_type_component = pd.merge(
+    cobie_component_df[[
+        'Name','TypeName', 'Space',
+        'ExtObject', 'ExtIdentifier', 'SerialNumber',
+    ]],
+    cobie_type_df[[
+        'TypeName', 'Category', 'Description',
+        'Manufacturer', 'ModelNumber', 
+        'TypeExtObject', 'TypeExtIdentifier',
+    ]],
+    on='TypeName',
+    how='left', 
+)
+
+
+# In[4]:
+
+cobie_system_df.rename(columns={
+    'Name':'SystemName',
+    'Description':'SystemDescription',
+    'Category':'SystemCategory',
+    'ComponentNames':'Name',
+}, inplace=True)
+system_all = cobie_system_df.explode(column='Name')
+
+cobie_flat = pd.merge(
+    cobie_type_component,
+    system_all[[
+        'SystemName', 'SystemDescription', 'SystemCategory',
+        'Name', 
+    ]],
+    on='Name',
+    how='left', 
+)
+
+cobie_flat = cobie_flat[[
+    'Name',
+    'TypeName', 
+    'Description',
+    'Category',
+    'SystemName',
+    'SystemDescription',
+    'SystemCategory',
+    'Space',
+    'ExtObject',
+    'ExtIdentifier',
+    'SerialNumber',
+    'Manufacturer',
+    'ModelNumber',
+    'TypeExtObject',
+    'TypeExtIdentifier',
+
+]]
+
+
+
+# In[5]:
+
+
+
+# In[7]:
+
+
+
+# In[8]:
+
+
+
+# In[9]:
+
+
+# In[10]:
+
+
+
+# In[11]:
+
+
+
+# In[12]:
+
+
+
+# In[13]:
+
+
+
+
+# In[ ]:
+
+project_id_button = st.text_input("Project ID", key="project_id")
+
+# In[ ]:
+
+if project_id_button:
+
+    project_id = st.session_state.project_id
+    with st.spinner(text="In progress, this may take some time..."):
+        # db = sqlalchemy.create_engine(postgres_string)
+        # conn = psycopg2.connect(
+        #     dbname="EIR-BEP",
+        #     host="activodb.cnwtnluwiep3.eu-west-1.rds.amazonaws.com",
+        #     user="ianyeo",
+        #     password=password
+        # )
+        # st.write("Connected to database", str(conn))
+        project_responsibility_query = 'SELECT * from "projectResponsibility"'
+        project_specific_responsibility_query = f'SELECT * from "projectResponsibility" WHERE project_id = {project_id}'
+        raci_query = 'SELECT * from "raci"'
+        responsibility_query = 'SELECT * from "responsibility"'
+        project_responsibility_raci_query = 'SELECT * from "projectResponsibilityRACI"'
+        project_responsibility_raci_orgnanisation_query = 'SELECT * from "projectResponsibilityRACIorganisation"'
+        project_organisaion_query = 'SELECT po.organisation_id, org.name, org.organisation_codes FROM "projectorganisation" AS po JOIN "organisation" AS org ON po.organisation_id = org.id WHERE po.project_id = %(project_id)s'
+        test_query = '''
+            SELECT
+                precomputed.id
+            FROM rnc_rna_precomputed precomputed
+            JOIN rnc_taxonomy tax
+            ON
+                tax.id = precomputed.taxid
+            WHERE
+                tax.lineage LIKE 'cellular organisms; Bacteria; %%'
+            AND precomputed.is_active = true    -- exclude sequences without active cross-references
+            AND rna_type = 'rRNA'
+        '''
+        test_query2 = '''
+            SELECT
+                upi,     -- RNAcentral URS identifier
+                taxid,   -- NCBI taxid
+                ac       -- external accession
+            FROM xref
+            WHERE ac IN ('OTTHUMT00000106564.1', 'OTTHUMT00000416802.1')
+        '''
+        rows = run_query(project_specific_responsibility_query)
+        raci = pd.read_sql_query(raci_query, get_connection(), params={'project_id':project_id})
+        # test_data = pd.read_sql_query(test_query2, get_connection())
+
+        # project_responsibilities = pd.read_sql_query(project_responsibility_query, db, params={'project_id':project_id})
+        # responsibility = pd.read_sql_query(responsibility_query, db, params={'project_id':project_id})
+        # project_responsibility_raci = pd.read_sql_query(project_responsibility_raci_query, db, params={'project_id':project_id})
+        # project_organisaion = pd.read_sql_query(project_organisaion_query, db, params={'project_id':project_id})
+
+    # st.dataframe(project_organisaion)
+    st.dataframe(raci)
+
+    create_template_table = st.text_input("test", key="test")
+
+    if create_template_table:
+
+        download_table = st.session_state.test
+        # raci_table = create_raci_table(project_responsibilities, responsibility, project_responsibility_raci)
+
+