jacob-mathison/doczyai-pipelines
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Activity

For UI 2 - Wrote comments that identify hardcodings and provide recommendations on a potential better approach.

Browse Source
This commit is contained in:
AARETE\agupta
2024-06-05 10:15:14 -05:00
parent 8e51457949
commit 5bd2ce5972
1 changed files with 10 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
streamlit/interface_2.py
+10 -10
View File
@@ -21,7 +21,7 @@ import re
from sf_conn import get_snowflake_conn
REDIRECT_URI = 'https://doczydev.aarete.com:8502'
user_list = USER_LIST
user_list = USER_LIST # RECOMMENDATION - AWS Secrets Manager or Snowflake
st.set_page_config(layout = "wide")
# Sidebar contents
@@ -39,10 +39,10 @@ with st.sidebar:
_,c1= st.columns([5,1])
try:
util.setup_page(REDIRECT_URI)
util.setup_page(REDIRECT_URI) # RECOMMENDATION - Not secure enough
except:
st.write("SSO Failed")
st.session_state['user_info'] = {'mail': 'maamseek@aarete.com', 'displayName': 'Mayank Aamseek'}
st.session_state['user_info'] = {'mail': 'maamseek@aarete.com', 'displayName': 'Mayank Aamseek'} # RECOMMENDATION - Remove after dev phase
try:
c1.write(f"User: **{st.session_state.user_info['displayName']}**")
user_mail = st.session_state.user_info['mail']
@@ -54,21 +54,21 @@ except KeyError as e:
try:
conn = get_snowflake_conn('STG')
cur = conn.cursor()
query = 'select * from "TRAINING_DATA_RAW"'
query = 'select * from "TRAINING_DATA_RAW"' # RECOMMENDATION - Move all queries to another file like constants
cur.execute(query)
field_values = pd.DataFrame.from_records(iter(cur), columns=[x[0] for x in cur.description])
field_values['Document_Name'] = field_values['DOCUMENT_NAME']
field_values['Document_Name'] = field_values['DOCUMENT_NAME'] # RECOMMENDATION - Use String Matching or something less hardcoded
except:
# field_values = pd.read_csv('contract_field_values.csv', encoding='unicode_escape', skipinitialspace=True)
# field_values = field_values.loc[:, ~field_values.columns.str.contains('Unnamed:')]
st.write("Conn failed, unable to fetch data from training data table in Snowflake")
try:
query = 'select * from "PROMPT_CONFIG"'
query = 'select * from "PROMPT_CONFIG"' # RECOMMENDATION - Move query somewhere else
cur.execute(query)
fields = pd.DataFrame.from_records(iter(cur), columns=[x[0] for x in cur.description])
fields.rename(columns={'FIELD_DESC': 'Field Name'}, inplace = True)
fields.rename(columns={'FIELD_DESC': 'Field Name'}, inplace = True) # RECOMMENDATION - Package into less hardcoded function or handle in DB
fields.rename(columns={'PROMPT': 'Interrogation Question?'}, inplace = True)
fields.rename(columns={'GROUP_ID': 'PRIORITY'}, inplace = True)
fields.rename(columns={'FIELD_NAME': 'SF_DB_COL_NAME'}, inplace = True)
@@ -103,13 +103,13 @@ field_row = st.columns([0.2, 0.7, 0.1])
with field_row[0]:
st.write("**Field Group**")
with field_row[1]:
field_group = st.selectbox('Field Group',('Unique Key', 'Contract Related', 'Pricing Before Carveouts - I'
field_group = st.selectbox('Field Group',('Unique Key', 'Contract Related', 'Pricing Before Carveouts - I' # RECOMMENDATION - Get from a separate list or snowflake
, 'Pricing Before Carveouts - II', 'Carveout Indicator, Code Type and Code #s - I'
, 'Carveout Indicator, Code Type and Code #s - II', 'Carveout Indicator, Code Type and Code #s - III'
, 'Optimize Carving Indic.', 'Carveout Method - I', 'Carveout Method - II', 'Provider'
, 'Timeline'), label_visibility = "collapsed")
if field_group == 'Unique Key':
if field_group == 'Unique Key': # RECOMMENDATION - Use a Dictionary for this mapping
fields = fields[fields['PRIORITY'] == 'A']
elif field_group == 'Contract Related':
fields = fields[fields['PRIORITY'] == 'C']
@@ -146,7 +146,7 @@ elif field_group == 'Timeline':
fields = fields[fields['PRIORITY'] == 'E']
if st.button("Show Results"):
query = 'select * from "DOCZY_PIPELINE_RAW_OUTPUT"'
query = 'select * from "DOCZY_PIPELINE_RAW_OUTPUT"' # RECOMMENDATION - Move query somewhere else
cur.execute(query)
df2 = pd.DataFrame.from_records(iter(cur), columns=[x[0] for x in cur.description])