Add fbprophet to prediction_techniques

gamestonk.py

@@ -1,7 +1,6 @@
 """ Example or something
 
 """
-
 import argparse
 import pandas as pd
 from helper_funcs import *
@@ -61,6 +60,7 @@ def load(l_args, s_ticker, s_start, s_interval, df_stock):
     else:
         print(f"Loading {s_intraday} {s_ticker} stock for analysis.")
 
+    print("")
     return [s_ticker, s_start, s_interval, df_stock]
 
 
@@ -184,10 +184,11 @@ def main():
     s_interval = "1440min"
 
     # Set stock by default to speed up testing
-    s_ticker = "AMZN"
+    s_ticker = "NIO"
     s_start = datetime.strptime("2020-06-04", "%Y-%m-%d")
     ts = TimeSeries(key=cfg.API_KEY_ALPHAVANTAGE, output_format='pandas')
-    df_stock, d_stock_metadata = ts.get_daily_adjusted(symbol=s_ticker, outputsize='full')  
+    df_stock, d_stock_metadata = ts.get_daily_adjusted(symbol=s_ticker, outputsize='full')
+    df_stock = df_stock.sort_index(ascending=True)
     df_stock = df_stock[s_start:] 
     # Delete above in the future
 

prediction_techniques/fbprophet.py

@@ -0,0 +1,61 @@
+import argparse
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+from pandas.plotting import register_matplotlib_converters
+register_matplotlib_converters()
+import datetime
+from datetime import datetime
+from alpha_vantage.timeseries import TimeSeries
+from helper_funcs import *
+from fbprophet import Prophet
+import warnings
+warnings.simplefilter("ignore")
+
+# ----------------------------------------------------- FBPROPHET -----------------------------------------------------
+def fbprophet(l_args, s_ticker, s_interval, df_stock):
+    parser = argparse.ArgumentParser(prog='fbprophet',
+                                     description="""Facebook Prophet is a forecasting procedure that is fast and provides 
+                                     completely automated forecasts that can be tuned by hand by data scientists and analysts.
+                                     It was developed by Facebook's data science team and is open source. """)
+
+    parser.add_argument('-d', "--days", action="store", dest="n_days", type=check_positive, default=5, help='prediction days')
+
+    try:
+        (ns_parser, l_unknown_args) = parser.parse_known_args(l_args)
+
+        if l_unknown_args:
+            print(f"The following args couldn't be interpreted: {l_unknown_args}\n")
+            return
+
+        df_stock = df_stock.sort_index(ascending=True)
+        df_stock.reset_index(level=0, inplace=True)
+        df_stock = df_stock[['date', '5. adjusted close']]
+        df_stock = df_stock.rename(columns={"date": "ds", "5. adjusted close": "y"})
+        df_stock['ds'] = pd.to_datetime(df_stock['ds'])
+
+        model = Prophet(yearly_seasonality=False, daily_seasonality=False)
+        model.fit(df_stock)
+
+        l_pred_days = get_next_stock_market_days(last_stock_day=pd.to_datetime(df_stock['ds'].values[-1]), n_next_days=ns_parser.n_days)
+        close_prices = model.make_future_dataframe(periods=ns_parser.n_days)
+        forecast = model.predict(close_prices)
+
+        fig, ax = plt.subplots()
+        model.plot(forecast, ax=ax, xlabel='Time', ylabel='Share Price ($)')
+        xmin, xmax, ymin, ymax = ax.axis()
+        ax.vlines(df_stock['ds'].values[-1], ymin, ymax, linewidth=2, linestyle='--', color='k')
+        plt.axvspan(l_pred_days[0], l_pred_days[-1], facecolor='tab:orange', alpha=0.2)
+        plt.ylim(ymin, ymax)
+        plt.xlim(df_stock['ds'].values[0], get_next_stock_market_days(last_stock_day=l_pred_days[-1], n_next_days=1))
+        plt.title(f"Fb Prophet on {s_ticker} - {ns_parser.n_days} days prediction")
+        plt.show()
+
+        print("")
+        print("Prediction prices:")
+        df_pred = forecast['yhat'][-ns_parser.n_days:].apply(lambda x: f"{x:.2f} $")
+        print(df_pred.to_string(index=False))
+        print("")
+
+    except:
+        print("")

prediction_techniques/pred_menu.py

@@ -13,6 +13,7 @@ from prediction_techniques import sma
 from prediction_techniques import knn
 from prediction_techniques import regression
 from prediction_techniques import arima
+from prediction_techniques import fbprophet
 
 # -----------------------------------------------------------------------------------------------------------------------
 def print_prediction(s_ticker, s_start, s_interval):
@@ -37,6 +38,7 @@ def print_prediction(s_ticker, s_start, s_interval):
     print("   cubic       cubic regression (polynomial 3)")
     print("   regression  regression (other polynomial)")
     print("   arima       autoregressive integrated moving average")
+    print("   prophet     Facebook's prophet prediction")
     #print("   arima")
     #print("   rnn")
     #print("   lstm")
@@ -52,7 +54,7 @@ def pred_menu(df_stock, s_ticker, s_start, s_interval):
     pred_parser.add_argument('cmd', choices=['help', 'q', 'quit',
                                              'sma', 'knn', 
                                              'linear', 'quadratic', 'cubic', 'regression',
-                                             'arima'])
+                                             'arima', 'prophet'])
 
     print_prediction(s_ticker, s_start, s_interval)
 
@@ -105,6 +107,10 @@ def pred_menu(df_stock, s_ticker, s_start, s_interval):
         elif ns_known_args.cmd == 'arima':
             arima.arima(l_args, s_ticker, s_interval, df_stock)
 
+        # ------------------------------------------------ FBPROPHET ------------------------------------------------
+        elif ns_known_args.cmd == 'prophet':
+            fbprophet.fbprophet(l_args, s_ticker, s_interval, df_stock)
+
         # ------------------------------------------------------------------------------------------------------------
         else:
             print("Command not recognized!")