Refactor app.py to replace Google Sheets integration with MongoDB. Removed gspread and related credentials, added pymongo for database connection. Updated data retrieval methods to fetch data from MongoDB collections. Adjusted UI elements and cleaned up unused code.

app.py

@@ -5,36 +5,21 @@ for name in dir():
     if not name.startswith('_'):
         del globals()[name]
 
-import pulp
 import numpy as np
 import pandas as pd
 import streamlit as st
-import gspread
 import gc
+import pymongo
 
 @st.cache_resource
 def init_conn():
-          scope = ['https://www.googleapis.com/auth/spreadsheets',
-                    "https://www.googleapis.com/auth/drive"]
-          
-          credentials = {
-            "type": "service_account",
-            "project_id": "sheets-api-connect-378620",
-            "private_key_id": "1005124050c80d085e2c5b344345715978dd9cc9",
-            "private_key": "-----BEGIN PRIVATE KEY-----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\nJuElxA33rFEjbgbzdyrE768=\n-----END PRIVATE KEY-----\n",
-            "client_email": "gspread-connection@sheets-api-connect-378620.iam.gserviceaccount.com",
-            "client_id": "106625872877651920064",
-            "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%40sheets-api-connect-378620.iam.gserviceaccount.com"
-          }
+        uri = st.secrets['mongo_uri']
+        client = pymongo.MongoClient(uri, retryWrites=True, serverSelectionTimeoutMS=500000)
+        db = client["PGA_Database"]
 
-          gc_con = gspread.service_account_from_dict(credentials)
-          
-          return gc_con
-
-gcservice_account = init_conn()
+        return db
+    
+db = init_conn()
 
 dk_player_url = 'https://docs.google.com/spreadsheets/d/1lMLxWdvCnOFBtG9dhM0zv2USuxZbkogI_2jnxFfQVVs/edit#gid=1828092624'
 CSV_URL = 'https://docs.google.com/spreadsheets/d/1lMLxWdvCnOFBtG9dhM0zv2USuxZbkogI_2jnxFfQVVs/edit#gid=1828092624'
@@ -44,50 +29,41 @@ player_roo_format = {'Top_finish': '{:.2%}','Top_5_finish': '{:.2%}', 'Top_10_fi
 
 @st.cache_resource(ttl = 600)
 def init_baselines():
-    sh = gcservice_account.open_by_url(dk_player_url)
-    worksheet = sh.worksheet('ROO')
-    raw_display = pd.DataFrame(worksheet.get_all_records())
-    data_cols = raw_display.columns.drop('Player')
-    raw_display[data_cols] = raw_display[data_cols].apply(pd.to_numeric, errors='coerce')
-    roo_data = raw_display
-    
-    worksheet = sh.worksheet('DK_CSV')
-    draftkings_data = pd.DataFrame(worksheet.get_all_records())
-    draftkings_data.rename(columns={"Name": "Player"}, inplace = True)
+    collection = db["PGA_Range_of_Outcomes"] 
+    cursor = collection.find()
+    player_frame = pd.DataFrame(cursor)
+    data_cols = player_frame.columns.drop('Player')
+    player_frame[data_cols] = player_frame[data_cols].apply(pd.to_numeric, errors='coerce')
+    roo_data = player_frame
     
-    return roo_data, draftkings_data
+    return roo_data
 
 def convert_df_to_csv(df):
     return df.to_csv().encode('utf-8')
 
-roo_data, draftkings_data = init_baselines()
+roo_data = init_baselines()
 hold_display = roo_data
-csv_data = draftkings_data
-csv_merge = pd.merge(csv_data, hold_display, how='left', left_on=['Player'], right_on = ['Player'])
-id_dict = dict(zip(csv_merge['Player'], csv_merge['Name + ID']))
 lineup_display = []
 check_list = []
 rand_player = 0
 boost_player = 0
 salaryCut = 0
 
-tab1, tab2 = st.tabs(["Player Overall Projections", "Optimizer"])
+tab1, tab2 = st.tabs(["Player Overall Projections", "Not Ready Yet"])
 
 with tab1:
     if st.button("Reset Data", key='reset1'):
               # Clear values from *all* all in-memory and on-disk data caches:
               # i.e. clear values from both square and cube
               st.cache_data.clear()
-              roo_data, draftkings_data = init_baselines()
+              roo_data = init_baselines()
               hold_display = roo_data
-              csv_data = draftkings_data
-              csv_merge = pd.merge(csv_data, hold_display, how='left', left_on=['Player'], right_on = ['Player'])
-              id_dict = dict(zip(csv_merge['Player'], csv_merge['Name + ID']))
               lineup_display = []
               check_list = []
               rand_player = 0
               boost_player = 0
               salaryCut = 0
+    
     hold_container = st.empty()
     display = hold_display.set_index('Player')
     st.dataframe(display.style.background_gradient(axis=0).background_gradient(cmap='RdYlGn').format(player_roo_format, precision=2), height=750, use_container_width = True)
@@ -99,168 +75,4 @@ with tab1:
     )
 
 with tab2:
-    col1, col2 = st.columns([1, 4])
-    
-    with col1:
-      
-        max_sal = st.number_input('Max Salary', min_value = 35000, max_value = 50000, value = 50000, step = 100)
-        min_sal = st.number_input('Min Salary', min_value = 35000, max_value = 49900, value = 49000, step = 100)
-        proj_cut = st.number_input('Lowest median allowed', min_value = 0, max_value = 100, value = 25, step = 1)
-        slack_var = st.number_input('Median randomness', min_value = 0, max_value = 5, value = 0, step = 1)
-        totalRuns_raw = st.number_input('How many Lineups', min_value = 1, max_value = 1000, value = 5, step = 1)
-        
-
-    totalRuns = totalRuns_raw
-    cut_group_1 = []
-    cut_group_2 = []
-    force_group_1 = []
-    force_group_2 = []
-    avoid_players = []
-    lock_player = []
-    lineups = []
-    player_pool_raw = []
-    
-    player_pool = []
-    player_count = []
-    player_trim_pool = []
-    portfolio = pd.DataFrame()
-    x = 1
-
-    if st.button('Optimize'):
-        max_proj = 1000
-        max_own = 1000
-        total_proj = 0
-        total_own = 0
-        
-        with col2:
-            with st.spinner('Wait for it...'):
-                with hold_container.container():
-
-                        while x <= totalRuns:
-
-                            raw_proj_file = hold_display
-                            raw_flex_file = raw_proj_file.dropna(how='all')
-                            raw_flex_file = raw_flex_file.loc[raw_flex_file['Median'] > 0]
-                            raw_flex_file = raw_flex_file.loc[raw_flex_file['Median'] > proj_cut]
-                            flex_file = raw_flex_file
-                            flex_file = flex_file[['Player', 'Salary', 'Median', 'Own', 'LevX']]
-                            flex_file.rename(columns={"Own": "Proj DK Own%"}, inplace = True)
-                            flex_file['name_var'] = flex_file['Player']
-                            flex_file['lock'] = flex_file['Player'].isin(lock_player)*1
-                            flex_file['Pos'] = 'G'
-                            flex_file = flex_file[['Player', 'name_var', 'Pos', 'Salary', 'Median', 'Proj DK Own%', 'lock', 'LevX']]
-                            if x > 1:
-                                if slack_var > 0:
-                                    flex_file['randNumCol'] = np.random.randint(-int(slack_var),int(slack_var), flex_file.shape[0])
-                                elif slack_var ==0:
-                                    flex_file['randNumCol'] = 0
-                            elif x == 1:
-                                flex_file['randNumCol'] = 0
-                            flex_file['Median'] = flex_file['Median'] + flex_file['randNumCol']
-                            flex_file_check = flex_file
-                            check_list.append(flex_file['Median'][4])
-                            player_ids = flex_file.index
-                            
-                            overall_players = flex_file[['Player']]
-                            overall_players['player_var_add'] = flex_file.index
-                            overall_players['player_var'] = 'player_vars_' + overall_players['player_var_add'].astype(str)
-
-                            player_vars = pulp.LpVariable.dicts("player_vars", flex_file.index, 0, 1, pulp.LpInteger)
-                            total_score = pulp.LpProblem("Fantasy_Points_Problem", pulp.LpMaximize)
-                            player_match = dict(zip(overall_players['player_var'], overall_players['Player']))
-                            player_index_match = dict(zip(overall_players['player_var'], overall_players['player_var_add']))
-                            player_own = dict(zip(flex_file['Player'], flex_file['Proj DK Own%']))
-                            player_sal = dict(zip(flex_file['Player'], flex_file['Salary']))
-                            player_lev = dict(zip(flex_file['Player'], flex_file['LevX']))
-                            player_proj = dict(zip(flex_file['Player'], flex_file['Median']))
-
-                            obj_points = {idx: (flex_file['Median'][idx]) for idx in flex_file.index}
-                            total_score += sum([player_vars[idx]*obj_points[idx] for idx in flex_file.index])
-
-                            obj_points_max = {idx: (flex_file['Median'][idx]) for idx in flex_file.index}
-                            obj_own_max = {idx: (flex_file['Proj DK Own%'][idx]) for idx in flex_file.index}
-
-                            obj_salary = {idx: (flex_file['Salary'][idx]) for idx in flex_file.index}
-                            total_score += pulp.lpSum([player_vars[idx]*obj_salary[idx] for idx in flex_file.index]) <= max_sal
-                            total_score += pulp.lpSum([player_vars[idx]*obj_salary[idx] for idx in flex_file.index]) >= min_sal
-
-                            for flex in flex_file['Pos'].unique():
-                                sub_idx = flex_file[flex_file['Pos'] != "Var"].index
-                                total_score += pulp.lpSum([player_vars[idx] for idx in sub_idx]) == 6
-
-                            player_count = []
-                            player_trim = []
-                            lineup_list = []
-
-                            total_score += pulp.lpSum([player_vars[idx]*obj_points_max[idx] for idx in flex_file.index]) <= max_proj - .01
-
-                            total_score.solve()
-                            for v in total_score.variables():
-                                if v.varValue > 0:
-                                    lineup_list.append(v.name)
-                            df = pd.DataFrame(lineup_list)
-                            df['Names'] = df[0].map(player_match)
-                            df['Cost'] = df['Names'].map(player_sal)
-                            df['Proj'] = df['Names'].map(player_proj)
-                            df['Own'] = df['Names'].map(player_own)
-                            total_cost = sum(df['Cost'])
-                            total_own = sum(df['Own'])
-                            total_proj = sum(df['Proj'])
-                            lineup_raw = pd.DataFrame(lineup_list)
-                            lineup_raw['Names'] = lineup_raw[0].map(player_match)
-                            lineup_raw['value'] = lineup_raw[0].map(player_index_match)
-                            lineup_final = lineup_raw.sort_values(by=['value'])
-                            del lineup_final[lineup_final.columns[0]]
-                            del lineup_final[lineup_final.columns[1]]
-                            lineup_final = lineup_final.reset_index(drop=True)
-                            lineup_test = lineup_final
-                            lineup_final = lineup_final.T
-                            lineup_final['Cost'] = total_cost
-                            lineup_final['Proj'] = total_proj
-                            lineup_final['Own'] = total_own
-
-                            if total_cost < 50001:
-                                lineups.append(lineup_final)
-                            
-                            lineup_test['Salary'] = lineup_test['Names'].map(player_sal)
-                            lineup_test['Proj'] = lineup_test['Names'].map(player_proj)
-                            lineup_test['Own'] = lineup_test['Names'].map(player_own)
-                            lineup_test['LevX'] = lineup_test['Names'].map(player_lev)
-                            lineup_test.loc['Column_Total'] = lineup_test.sum(numeric_only=True, axis=0)
-                            
-                            lineup_display.append(lineup_test)
-                            
-                            with col2:
-                                with st.container():
-                                    st.table(lineup_test)
-
-                            max_proj = total_proj
-                            max_own = total_own
-
-                            check_list.append(total_proj)
-
-                            portfolio = pd.concat([portfolio, lineup_final], ignore_index=True)
-
-                            x += 1
-                        
-                        portfolio.rename(columns={0: "Player_1", 1: "Player_2", 2: "Player_3", 3: "Player_4", 4: "Player_5", 5: "Player_6"}, inplace = True)
-                        portfolio = portfolio.dropna()
-
-                        final_outcomes = portfolio
-                        final_outcomes['p1 id'] = final_outcomes['Player_1'].map(id_dict)
-                        final_outcomes['p2 id'] = final_outcomes['Player_2'].map(id_dict)
-                        final_outcomes['p3 id'] = final_outcomes['Player_3'].map(id_dict)
-                        final_outcomes['p4 id'] = final_outcomes['Player_4'].map(id_dict)
-                        final_outcomes['p5 id'] = final_outcomes['Player_5'].map(id_dict)
-                        final_outcomes['p6 id'] = final_outcomes['Player_6'].map(id_dict)
-                        final_outcomes = final_outcomes[['p1 id', 'p2 id', 'p3 id', 'p4 id', 'p5 id', 'p6 id']]
-                        with col1:
-                          st.download_button(
-                              label="Export Lineups",
-                              data=convert_df_to_csv(final_outcomes),
-                              file_name='PGA_DFS_export.csv',
-                              mime='text/csv',
-                          )
-        
-                with hold_container:
-                    hold_container = st.empty()
+     st.write("Not Ready Yet")

requirements.txt

@@ -2,7 +2,7 @@ streamlit
 gspread
 openpyxl
 matplotlib
-streamlit-aggrid
+pymongo
 pulp
 docker
 plotly