James McCool
Refactor PDF export functionality in app.py to use ReportLab
d581c52
raw
history blame
10.6 kB
import streamlit as st
st.set_page_config(layout="wide")
for name in dir():
if not name.startswith('_'):
del globals()[name]
import numpy as np
import pandas as pd
import streamlit as st
import gspread
from reportlab.lib import colors
from reportlab.lib.pagesizes import letter, landscape
from reportlab.platypus import SimpleDocTemplate, Table, TableStyle
from io import BytesIO
@st.cache_resource
def init_conn():
scope = ['https://spreadsheets.google.com/feeds', 'https://www.googleapis.com/auth/drive']
credentials = {
"type": "service_account",
"project_id": "model-sheets-connect",
"private_key_id": st.secrets['model_sheets_connect_pk'],
"private_key": "-----BEGIN PRIVATE KEY-----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\nF/j9eUXfXjAlb042MphoF3ZC\n-----END PRIVATE KEY-----\n",
"client_email": "[email protected]",
"client_id": "100369174533302798535",
"auth_uri": "https://accounts.google.com/o/oauth2/auth",
"token_uri": "https://oauth2.googleapis.com/token",
"auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
"client_x509_cert_url": "https://www.googleapis.com/robot/v1/metadata/x509/gspread-connection%40model-sheets-connect.iam.gserviceaccount.com"
}
gc_con = gspread.service_account_from_dict(credentials, scope)
return gc_con
gcservice_account = init_conn()
NHL_data = st.secrets['NHL_Data']
percentages_format = {'Shots': '{:.2%}', 'HDCF': '{:.2%}', 'Goals': '{:.2%}', 'Assists': '{:.2%}', 'Blocks': '{:.2%}',
'L14_Shots': '{:.2%}', 'L14_HDCF': '{:.2%}', 'L14_Goals': '{:.2%}', 'L14_Assists': '{:.2%}',
'L14_Blocks': '{:.2%}', 'Max Goal%': '{:.2%}', 'L14 Max Goal%': '{:.2%}'}
matchups_format = {'HDCF%': '{:.2%}', 'o_HDCA%': '{:.2%}', 'HDCF_m%': '{:.2%}'}
@st.cache_resource(ttl = 599)
def init_baselines():
parse_hold = pd.DataFrame(columns=['Line', 'SK1', 'SK2', 'SK3', 'Cost', 'Team Total', 'Shots', 'HDCF', 'Goals', 'Assists', 'Blocks',
'L14_Shots', 'L14_HDCF', 'L14_Goals', 'L14_Assists', 'L14_Blocks', 'Max Goal%'])
sh = gcservice_account.open_by_url(NHL_data)
worksheet = sh.worksheet('Player_Level_ROO')
raw_display = pd.DataFrame(worksheet.get_values())
raw_display.columns = raw_display.iloc[0]
raw_display = raw_display[1:]
raw_display = raw_display.reset_index(drop=True)
raw_display = raw_display[raw_display['Opp'] != ""]
team_frame = raw_display[['Team', 'Opp']]
team_list = team_frame['Team'].unique()
team_dict = dict(zip(team_frame['Team'], team_frame['Opp']))
worksheet = sh.worksheet('Matchups')
raw_display = pd.DataFrame(worksheet.get_values())
raw_display.columns = raw_display.iloc[0]
raw_display = raw_display[1:]
raw_display = raw_display.reset_index(drop=True)
raw_display = raw_display[raw_display['Opp'] != ""]
matchups = raw_display[['Team', 'Opp', 'FL1$', 'FL2$', 'FL3$', 'Team Total', 'Game Pace', 'SF', 'o_SA', 'SF_m', 'HDCF',
'o_HDCA', 'HDCF_m', 'HDCF%', 'o_HDCA%', 'HDCF_m%', 'HDSF+']]
data_cols = matchups.columns.drop(['Team', 'Opp'])
matchups[data_cols] = matchups[data_cols].apply(pd.to_numeric, errors='coerce')
matchups = matchups.dropna(subset='FL1$')
matchups = matchups.sort_values(by='HDCF_m', ascending=False)
worksheet = sh.worksheet('Marketshares')
raw_display = pd.DataFrame(worksheet.get_values())
raw_display.columns = raw_display.iloc[0]
raw_display = raw_display[1:]
raw_display = raw_display.reset_index(drop=True)
# raw_display = raw_display[raw_display['Line'] != ""]
overall_ms = raw_display[['Line', 'SK1', 'SK2', 'SK3', 'Cost', 'Team Total', 'Shots', 'HDCF', 'Goals', 'Assists', 'Blocks',
'L14_Shots', 'L14_HDCF', 'L14_Goals', 'L14_Assists', 'L14_Blocks']]
pat = '|'.join(team_list)
s = overall_ms['Line'].str.extract('('+ pat + ')', expand=False)
overall_ms['Max Goal%'] = overall_ms.groupby(s)['Goals'].transform('max')
overall_ms['L14 Max Goal%'] = overall_ms.groupby(s)['L14_Goals'].transform('max')
data_cols = overall_ms.columns.drop(['Line', 'SK1', 'SK2', 'SK3'])
overall_ms[data_cols] = overall_ms[data_cols].apply(pd.to_numeric, errors='coerce')
overall_ms['Proj Goal'] = overall_ms['Goals'] * overall_ms['Team Total']
overall_ms['L14 Proj Goal'] = overall_ms['L14_Goals'] * overall_ms['Team Total']
overall_ms = overall_ms[['Line', 'SK1', 'SK2', 'SK3', 'Cost', 'Team Total', 'Shots', 'HDCF', 'Goals', 'Max Goal%', 'Proj Goal',
'Assists', 'Blocks', 'L14_Shots', 'L14_HDCF', 'L14_Goals', 'L14 Max Goal%', 'L14 Proj Goal', 'L14_Assists', 'L14_Blocks']]
overall_ms = overall_ms.sort_values(by='Shots', ascending=False)
return matchups, overall_ms, team_frame, team_list, team_dict
def convert_df_to_csv(df):
return df.to_csv().encode('utf-8')
def convert_df_to_pdf(df):
try:
# Create a buffer to receive PDF data
buffer = BytesIO()
# Create the PDF object using the buffer as its "file"
doc = SimpleDocTemplate(buffer, pagesize=landscape(letter))
# Convert DataFrame to a list of lists for the table
data = [df.columns.tolist()] + df.values.tolist()
# Create the table
table = Table(data)
# Add style to the table
style = TableStyle([
('BACKGROUND', (0, 0), (-1, 0), colors.grey),
('TEXTCOLOR', (0, 0), (-1, 0), colors.whitesmoke),
('ALIGN', (0, 0), (-1, -1), 'CENTER'),
('FONTNAME', (0, 0), (-1, 0), 'Helvetica-Bold'),
('FONTSIZE', (0, 0), (-1, 0), 10),
('BOTTOMPADDING', (0, 0), (-1, 0), 12),
('BACKGROUND', (0, 1), (-1, -1), colors.white),
('TEXTCOLOR', (0, 1), (-1, -1), colors.black),
('FONTNAME', (0, 1), (-1, -1), 'Helvetica'),
('FONTSIZE', (0, 1), (-1, -1), 8),
('GRID', (0, 0), (-1, -1), 1, colors.black),
('ALIGN', (0, 0), (-1, -1), 'CENTER'),
('VALIGN', (0, 0), (-1, -1), 'MIDDLE'),
])
table.setStyle(style)
# Build the PDF
elements = [table]
doc.build(elements)
# Get the value of the BytesIO buffer
pdf = buffer.getvalue()
buffer.close()
return pdf
except Exception as e:
st.error(f"Error generating PDF: {str(e)}")
return None
matchups, overall_ms, team_frame, team_list, team_dict = init_baselines()
col1, col2 = st.columns([1, 9])
with col1:
if st.button("Reset Data", key='reset1'):
st.cache_data.clear()
matchups, overall_ms, team_frame, team_list, team_dict = init_baselines()
split_var1 = st.radio("View matchups or line marketshares?", ('Slate Matchups', 'Line Marketshares'), key='split_var1')
if split_var1 == "Line Marketshares":
team_var = st.radio("View all teams or specific teams?", ('All Teams', 'Specific Teams'), key='team_var')
if team_var == "All Teams":
team_split = team_frame.Team.values.tolist()
elif team_var == "Specific Teams":
team_split = st.multiselect('Which teams would you like to include in the tables?', options = team_frame['Team'].unique(), key='team_var1')
with col2:
if split_var1 == 'Slate Matchups':
display_table = matchups
display_table = display_table.set_index('Team')
st.dataframe(display_table.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(matchups_format, precision=2), height=500, use_container_width = True)
elif split_var1 == 'Line Marketshares':
display_table = overall_ms
display_parsed = display_table[display_table['Line'].str.contains('|'.join(team_split))]
display_parsed = display_parsed.set_index('Line')
st.dataframe(display_parsed.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(percentages_format, precision=2), height=500, use_container_width = True)
download_var = st.selectbox('What download would you like?', options = ['CSV', 'PDF'], key='download_var')
if st.button('Download'):
if download_var == 'CSV':
st.download_button(
label="Export Marketshares (CSV)",
data=convert_df_to_csv(display_table),
file_name='Marketshares_export.csv',
mime='text/csv',
)
elif download_var == 'PDF':
st.download_button(
label="Export Marketshares (PDF)",
data=convert_df_to_pdf(display_table),
file_name='Marketshares_export.pdf',
mime='application/pdf',
)