Refactor import statements across multiple files to replace 'fuzzywuzzy' with 'rapidfuzz' for improved performance and consistency in string matching functionality. Additionally, clean up unused imports in app.py and related global functions to enhance code clarity and maintainability.

app.py

@@ -1,11 +1,8 @@
 import streamlit as st
 st.set_page_config(layout="wide")
-import numpy as np
 import pandas as pd
-import time
-from rapidfuzz import process, fuzz
+from rapidfuzz import process
 import random
-import re
 from collections import Counter
 
 ## import global functions

global_func/clean_player_name.py

@@ -2,7 +2,6 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
 
 def clean_player_name(name):
     # Handle colon case first (remove everything before colon)

global_func/find_csv_mismatches.py

@@ -1,7 +1,7 @@
 import streamlit as st
 import numpy as np
 import pandas as pd
-from fuzzywuzzy import process
+from rapidfuzz import process
 
 def find_csv_mismatches(csv_df, projections_df):
     # Create copies of the dataframes to avoid modifying the originals

global_func/find_name_mismatches.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 
 def find_name_mismatches(portfolio_df, projections_df):
     """

global_func/get_portfolio_names.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 
 def get_portfolio_names(portfolio_df):
     """

global_func/highlight_rows.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 
 def highlight_changes(row):
     original_row = st.session_state['portfolio'].iloc[row.name]

global_func/load_csv.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 
 def load_csv(upload):
     if upload is not None:

global_func/load_dk_fd_file.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 import re
 
 def load_dk_fd_file(lineups, csv_file):

global_func/load_file.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 import re
 
 ## import global functions

global_func/load_ss_file.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 import re
 
 def load_ss_file(lineups, csv_file):

global_func/optimize_lineup.py

@@ -2,7 +2,7 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
+from rapidfuzz import process
 
 def optimize_lineup(row):
     current_lineup = []

global_func/predict_dupes.py

@@ -2,7 +2,6 @@ import streamlit as st
 import numpy as np
 import pandas as pd
 import time
-from fuzzywuzzy import process
 import math
 from difflib import SequenceMatcher
 

global_func/reduce_volatility_preset.py

@@ -1,5 +1,4 @@
 import pandas as pd
-import numpy as np
 
 def reduce_volatility_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols: list, sport: str):
     excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Diversity']

global_func/small_field_preset.py

@@ -1,5 +1,4 @@
 import pandas as pd
-import numpy as np
 
 def small_field_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols: list, sport: str):
     excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Diversity']

global_func/volatility_preset.py

@@ -1,5 +1,4 @@
 import pandas as pd
-import numpy as np
 
 def volatility_preset(portfolio: pd.DataFrame, lineup_target: int, exclude_cols: list, sport: str):
     excluded_cols = ['salary', 'median', 'Own', 'Finish_percentile', 'Dupes', 'Stack', 'Size', 'Win%', 'Lineup Edge', 'Weighted Own', 'Geomean', 'Diversity']

requirements.txt

@@ -1,11 +1,4 @@
 streamlit
-gspread
-openpyxl
-matplotlib
-rapidfuzz
-fuzzywuzzy
-pulp
-docker
-plotly
-scipy
-pymongo
+pandas
+numpy
+rapidfuzz