code refactor

README.md

@@ -7,5 +7,5 @@ methodology explanation can be found in medium article: https://medium.com/@xben
 
 Code: 
 * main: main.py
-* data: use library_data.py. Data can be pre-saved in output folder for easier check.
+* data: use library_data.py. This file will pre save data into csv in the output folder.
 * logic (imp loss, range, coverage %): library_logic.py

lib_const.py

@@ -0,0 +1,31 @@
+
+
+pool_info_list = [
+    ['0xcbcdf9626bc03e24f779434178a73a0b4bad62ed', 'WBTC',  'WETH',  0.003],
+    ['0x88e6a0c2ddd26feeb64f039a2c41296fcb3f5640' , 'USDC', 'WETH', ],
+    ['0x5777d92f208679db4b9778590fa3cab3ac9e2168' , 'DAI', 'USDC', ], 
+    ['0x109830a1aaad605bbf02a9dfa7b0b92ec2fb7daa', 'WSTETH', 'WETH',],
+    ['0x4585fe77225b41b697c938b018e2ac67ac5a20c0' , 'WBTC' ,'WETH', 0.0005]
+]
+
+# data needed by coingecko API
+price_token_list =[
+    ['bitcoin', 'BTC' ],
+    ['ethereum',  'ETH']
+]
+
+def get_pool_filename(pool_address, token0=None, token1=None):    
+    if token0 is None or token1 is None:
+        for pool_info in pool_info_list:
+            if pool_info[0] == pool_address:
+                token0 = pool_info[1]
+                token1 = pool_info[2]
+                break
+
+    file_name_addon = "_".join([pool_address, token0, token1])
+    file_name = 'output/pool_data_' + file_name_addon + '.csv'
+    return file_name
+
+
+#    date_begin = datetime.strptime(date_begin_yyyymmdd, '%Y%m%d')
+#    date_end = datetime.strptime(date_end_yyyymmdd, '%Y%m%d')

lib_data.py

@@ -0,0 +1,153 @@
+import requests
+from datetime import datetime, timedelta
+import pandas as pd
+
+
+# API each time can only get 100 recoreds, hence break down the retrieve into year-month
+def get_uniswap_v3_data_limit100(pool_address, from_timestamp, to_timestamp):
+    # Uniswap V3 Subgraph endpoint
+    endpoint = 'https://api.thegraph.com/subgraphs/name/uniswap/uniswap-v3'
+
+    # GraphQL query to get historical data
+    query = '''
+    {
+    poolDayDatas( orderBy: date, 
+    where: { pool: "%s", date_gte: %d, date_lte: %d } ) {
+        date
+        liquidity
+        sqrtPrice
+        token0Price
+        token1Price
+        volumeToken0
+        volumeToken1
+        feesUSD
+      	volumeUSD
+      	tvlUSD
+    }
+    }
+
+    ''' % (pool_address, from_timestamp, to_timestamp)
+    # print(query)
+    # Make the GraphQL request
+    response = requests.post(endpoint, json={'query': query})
+    data = response.json()
+    #print(data)
+    return data['data']['poolDayDatas']
+
+def last_day_of_month(year, month):
+    # Calculate the first day of the next month
+    first_day_of_next_month = datetime(year, month, 1) + timedelta(days=32)
+
+    # Subtract one day to get the last day of the current month
+    last_day_of_month = first_day_of_next_month.replace(day=1) - timedelta(days=1)
+
+    return last_day_of_month
+
+
+def get_uniswap_v3_data_year(pool_address, years):
+    pool_df=pd.DataFrame()
+
+    # Get Uniswap V3 data
+    for year in years:
+        for month in range(1, 13):
+
+            from_timestamp = int(datetime(year, month, 1).timestamp())  # Replace with your start date
+            next_mon_first_day = last_day_of_month(year, month)+ timedelta(days=1)
+            to_timestamp = int(next_mon_first_day.timestamp())
+            uniswap_v3_data_month = get_uniswap_v3_data_limit100(pool_address, from_timestamp, to_timestamp)
+            df = pd.DataFrame(uniswap_v3_data_month)
+            pool_df = pd.concat([pool_df, df], ignore_index=True)
+
+    return pool_df
+
+def get_crypto_price(symbol, token, start_date, end_date, vs_currency='usd'):
+    url = f"https://api.coingecko.com/api/v3/coins/{symbol}/market_chart"
+    params = {
+        'vs_currency': vs_currency,
+        'from': int(start_date.timestamp()),
+        'to': int(end_date.timestamp()),
+        'interval': 'daily',
+        'days': 1200
+    }
+
+    response = requests.get(url, params=params)
+
+    if response.status_code == 200:
+        data = response.json()
+        prices = data.get('prices', [])
+    else:
+        print(f"Error: {response.status_code}")
+        print(response.text)
+        return None
+
+    columns = ['date', 'price']
+    df = pd.DataFrame(prices, columns=columns) 
+    df.drop(df.index[-1], inplace=True) # last date has 2 records
+
+    df['date'] = df['date'].apply( lambda x: datetime.utcfromtimestamp(x / 1000).date()   )
+    df['token'] = token
+    df['vs_currency'] = vs_currency
+
+    return df
+
+
+
+
+
+# Check if the script is being run as the main program
+if __name__ == "__main__":
+
+    import lib_const
+
+    load_all_pool_related_data = True
+    if load_all_pool_related_data: # getting pool fee/vol related data
+
+        years = [2022, 2023]
+
+        result_df = pd.DataFrame()
+        for pool_info in lib_const.pool_info_list:
+            pool_address = pool_info[0]
+            result_df = get_uniswap_v3_data_year(pool_address, years)
+            file_name = lib_const.get_pool_filename(pool_address, token0=pool_info[1], token1=pool_info[2])
+            print("save data:",file_name )
+            result_df.to_csv(file_name, index=False)
+            #print("will only run for the first pool during test. ")
+            #break
+
+    # if only wanna run individual pool    
+    # pool_address = '0xcbcdf9626bc03e24f779434178a73a0b4bad62ed' #WBTC WETH 0.3%
+    # pool_address = '0x88e6a0c2ddd26feeb64f039a2c41296fcb3f5640' #USDC WETH
+    # pool_address = '0x5777d92f208679db4b9778590fa3cab3ac9e2168' #DAI USDC
+    # pool_address = '0x109830a1aaad605bbf02a9dfa7b0b92ec2fb7daa' #WSTETH WETH
+    # pool_address = '0x4585fe77225b41b697c938b018e2ac67ac5a20c0' #WBTC WETH, 0.05%
+    # result_df = get_uniswap_v3_data_year(pool_address, years)
+    # file_name = lib_const.get_pool_filename(pool_address)
+    # result_df.to_csv(file_name, index=False)
+    # Display the DataFrame
+    # result_df.head()
+
+
+    load_price_related_data = False;
+    if load_price_related_data: # getting pool fee/vol related data
+        # Set the start and end date
+        start_date = datetime(2020, 11, 1)
+        end_date = start_date + timedelta(days=1)
+
+
+        df = pd.DataFrame()
+        for token in lib_const.price_token_list:
+            token_name = token[0]
+            token_ticker = token[1] 
+            df_price = get_crypto_price(token_name, token_ticker , start_date, end_date)
+            print(f'get token {token_ticker} price in usd' )
+            df_price_btc = pd.DataFrame()
+            if(token_ticker != 'BTC'):
+                df_price_btc = get_crypto_price(token_name, token_ticker , start_date, end_date, vs_currency='btc')
+                print(f'get token {token_ticker} price in btc' )
+
+            df = pd.concat([df, df_price, df_price_btc], ignore_index=True)
+
+        price_file_name = 'output/price_data_all_token.csv'
+        df.to_csv(price_file_name, index=False)
+
+        print(f"DataFrame saved to {price_file_name}")

library_logic.py → lib_logic.py

@@ -1,10 +1,12 @@
 # function for full range LP
 import numpy as np
 import pandas as pd
+from datetime import datetime
+import lib_const
 
 # Get impermanent loss, qty_change_token0, and token1. 
-# code also works if input is array
-def get_impermanent_loss(price_change, is_change_token0=True, b_return_df = False, ret_imp_loss_only = False ):
+# code also works with  array input
+def get_impermanent_loss_without_range(price_change, is_change_token0=True, b_return_df = False, ret_imp_loss_only = False ):
     #input value check ignored here
     if(is_change_token0):
         price_change_token0 = np.array(price_change)
@@ -41,20 +43,9 @@ def get_impermanent_loss(price_change, is_change_token0=True, b_return_df = Fals
     return result_matrix
 
 
-def get_bin_price_range_same_liquidity(price_change):
-    return -price_change/(1+price_change)
-
-def get_liquidity_boost_by_range(prince_range, benchmark = -0.5):
-    if(benchmark > 0):
-        benchmark = get_bin_price_range_same_liquidity(benchmark)
-
-    boost  = (np.sqrt(1+benchmark) -1 )  / (np.sqrt(1+prince_range) -1 )
-    return boost
-
-
-def get_impermanent_loss_range_pos(price_change, price_range_down, is_change_token0=True, b_return_df = False):
+def get_impermanent_loss_given_range(price_change, price_range_down):
     #input value check ignored here
-    price_range_up = get_bin_price_range_same_liquidity(price_range_down)
+    price_range_up = get_opposite_bin_limit_with_same_liquidity(price_range_down)
 
     #print(price_change,price_range_down, price_range_up )
 
@@ -78,33 +69,56 @@ def get_impermanent_loss_range_pos(price_change, price_range_down, is_change_tok
     return imp_loss
 
 
-def get_ETHBTC_poolyield_daily(date_begin_yyyymmdd = "20090101", date_end_yyyymmdd = "30000101"):
+
+
+
+def get_opposite_bin_limit_with_same_liquidity(price_change):
+    return -price_change/(1+price_change)
+
+def get_liquidity_boost_given_range(prince_range, benchmark = -0.5):
+    if(benchmark > 0):
+        benchmark = get_opposite_bin_limit_with_same_liquidity(benchmark)
+
+    boost  = (np.sqrt(1+benchmark) -1 )  / (np.sqrt(1+prince_range) -1 )
+    return boost
+
+
+
+def get_ETHBTC_poolyield_daily(date_begin_yyyymmdd = "2009-01-01", date_end_yyyymmdd = "3000-01-01"):
     pool_address = '0xcbcdf9626bc03e24f779434178a73a0b4bad62ed'
-    data_file_name = 'output/output_' + pool_address + '.csv'
+    data_file_name = lib_const.get_pool_filename(pool_address)
+
     df = pd.read_csv(data_file_name)
 
+    date_begin = datetime.strptime(date_begin_yyyymmdd, '%Y-%m-%d')
+    date_end = datetime.strptime(date_end_yyyymmdd, '%Y-%m-%d')
+
+
     # Convert 'date' column to YYYYMMDD format
-    df['date_int'] = df['date']
-    df['date'] = pd.to_datetime(df['date'], unit='s').dt.strftime('%Y%m%d')
+    df['date'] = pd.to_datetime(df['date'], unit='s')
     df = df.sort_values(by='date',ascending=False)
 
-    df = df[(df['date'] >= date_begin_yyyymmdd) & (df['date'] <= date_end_yyyymmdd)]
+    df = df[(df['date'] >= date_begin) & (df['date'] <= date_end)]
 
     df['daily_fee_rate'] = df['feesUSD'] / df['tvlUSD']
     return np.average(df['daily_fee_rate'])
 
 def get_pool_performance_statistic(pool_address, token0, token1, fee_bps, year = -1):
 
-    data_file_name = 'output/output_' + pool_address + '.csv'
+    data_file_name = lib_const.get_pool_filename(pool_address)
+    # data_file_name = 'output/output_' + pool_address + '.csv'
     df = pd.read_csv(data_file_name)
 
     # Convert 'date' column to YYYYMMDD format
     df['date_int'] = df['date']
-    df['date'] = pd.to_datetime(df['date'], unit='s').dt.strftime('%Y%m%d')
-    df = df.sort_values(by='date',ascending=False)
+    df['date'] = pd.to_datetime(df['date'], unit='s')
+    df = df.sort_values(by='date',ascending=False)   
+
+    #df['date'] = pd.to_datetime(df['date'], unit='s').dt.strftime('%Y%m%d')
+
 
-    df['year'] = pd.to_datetime(df['date_int'], unit='s').dt.strftime('%Y')
-    df['YYYYMM'] = pd.to_datetime(df['date_int'], unit='s').dt.strftime('%Y%m')
+    df['year'] = df['date'].dt.strftime('%Y')
+    df['YYYYMM'] = df['date'].dt.strftime('%Y%m')
 
     # Filter rows where 'year' is not equal to 2023
     if (year != -1):
@@ -148,7 +162,7 @@ def get_pool_performance_statistic(pool_address, token0, token1, fee_bps, year =
 
 
     price_change_array = [total_pct_price_change, price_change_7d_95th, price_change_7d_5th]
-    df_pool_imp_loss_stats = get_impermanent_loss(price_change_array, b_return_df=True)
+    df_pool_imp_loss_stats = get_impermanent_loss_without_range(price_change_array, b_return_df=True)
 
 
     # Create a 1-row DataFrame
@@ -186,21 +200,21 @@ def get_pool_performance_statistic(pool_address, token0, token1, fee_bps, year =
     # print("test with range: -----")
 
     price_change = 0.05
-    loss = get_impermanent_loss_range_pos(price_change, price_range_down=-0.16)
+    loss = get_impermanent_loss_given_range(price_change, price_range_down=-0.16)
     print("imp loss",price_change, loss)
 
 
     price_change = -0.08
-    loss = get_impermanent_loss_range_pos(price_change, price_range_down=0.16)
+    loss = get_impermanent_loss_given_range(price_change, price_range_down=0.16)
     print("imp loss, all y gone",price_change, loss)
 
     your_range = -0.05
     benchmark = -0.15
-    print('boost:',your_range,benchmark, "by", get_liquidity_boost_by_range (your_range,benchmark))
+    print('boost:',your_range,benchmark, "by", get_liquidity_boost_given_range (your_range,benchmark))
 
     your_range =np.array([-0.05, -0.1]) 
     benchmark = -0.15
-    print('boost:',your_range,benchmark, "by", get_liquidity_boost_by_range (your_range,benchmark))
+    print('boost:',your_range,benchmark, "by", get_liquidity_boost_given_range (your_range,benchmark))
 
 
         # Load CSV into DataFrame
@@ -231,6 +245,6 @@ def get_pool_performance_statistic(pool_address, token0, token1, fee_bps, year =
     df_pool_stats.to_csv('output/result_pools.csv', index=False)
 
     print("pool daily yield", get_ETHBTC_poolyield_daily())
-    print("pool daily yield 2023:", get_ETHBTC_poolyield_daily(date_begin_yyyymmdd = "20230101"))
+    print("pool daily yield 2023:", get_ETHBTC_poolyield_daily(date_begin_yyyymmdd = "2023-01-01"))