Add application file

app.py

@@ -3,6 +3,14 @@ import streamlit as st
 import pandas as pd
 import datetime
 
+import numpy as np
+import matplotlib.pyplot as plt
+from keras.models import Sequential
+from keras.layers import LSTM
+from keras.layers import Dense
+from keras.layers import Bidirectional
+
+
 st.write("""
 # Simple Stock Price App
 
@@ -10,16 +18,66 @@ Shown are the stock **closing price** and **volume**.
 """)
 
 def user_input_features() :
-    stock_symbol = st.sidebar.selectbox('Symbol',('ANTM.JK','ARNA.JK', 'DUTI.JK', 'ELSA.JK', 
-    'MFMI.JK'))
+    stock_symbol = st.sidebar.selectbox('Symbol',('ANTM', 'ARNA', 'DUTI', 'ELSA', 'MFMI'))
     date_start = st.sidebar.date_input("Start Date", datetime.date(2015, 5, 31))
     date_end = st.sidebar.date_input("End Date", datetime.date.today())
 
-    tickerData = yf.Ticker(stock_symbol)
+    tickerData = yf.Ticker(stock_symbol+'.JK')
     tickerDf = tickerData.history(period='1d', start=date_start, end=date_end)
-    return tickerDf
+    return tickerDf, stock_symbol
 
-input_df = user_input_features()
+input_df, stock_symbol = user_input_features()
 
 st.line_chart(input_df.Close)
-st.line_chart(input_df.Volume)
+st.line_chart(input_df.Volume)
+
+st.write("""
+# Stock Price Prediction
+
+Shown are the stock prediction for next 20 days.
+""")
+
+n_steps = 100
+n_features = 1
+
+model = Sequential()
+model.add(Bidirectional(LSTM(300, activation='relu'), input_shape=(n_steps, n_features)))
+model.add(Dense(1))
+model.compile(optimizer='adam', loss='mse')
+
+model.load_weights(stock_symbol + ".h5")
+df = input_df.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
+df = df[df.Volume > 0]
+
+close = df['Close'][-n_steps:].to_list()
+min_in = min(close)
+max_in = max(close)
+in_seq = []
+for i in close :
+  in_seq.append((i - min_in) / (max_in - min_in))
+
+for i in range(20) :
+  x_input = np.array(in_seq[-100:])
+  x_input = x_input.reshape((1, n_steps, n_features))
+  yhat = model.predict(x_input, verbose=0)
+  in_seq.append(yhat[0][0])
+
+norm_res = in_seq[-20:]
+res = []
+for i in norm_res :
+  res.append(i * (max_in - min_in) + min_in)
+
+closepred = close[-80:]
+for x in res :
+  closepred.append(x)
+
+plt.figure(figsize = (20,10))
+plt.plot(closepred, label="Prediction")
+plt.plot(close[-80:], label="Previous")
+plt.ylabel('Price (Rp)', fontsize = 15 )
+plt.xlabel('Days', fontsize = 15 )
+plt.title(stock_symbol + " Stock Prediction", fontsize = 20)
+plt.legend()
+plt.grid()
+
+st.pyplot(plt)

myapp.py

@@ -1,83 +0,0 @@
-import yfinance as yf
-import streamlit as st
-import pandas as pd
-import datetime
-
-import numpy as np
-import matplotlib.pyplot as plt
-from keras.models import Sequential
-from keras.layers import LSTM
-from keras.layers import Dense
-from keras.layers import Bidirectional
-
-
-st.write("""
-# Simple Stock Price App
-
-Shown are the stock **closing price** and **volume**.
-""")
-
-def user_input_features() :
-    stock_symbol = st.sidebar.selectbox('Symbol',('ANTM', 'ARNA', 'DUTI', 'ELSA', 'MFMI'))
-    date_start = st.sidebar.date_input("Start Date", datetime.date(2015, 5, 31))
-    date_end = st.sidebar.date_input("End Date", datetime.date.today())
-
-    tickerData = yf.Ticker(stock_symbol+'.JK')
-    tickerDf = tickerData.history(period='1d', start=date_start, end=date_end)
-    return tickerDf, stock_symbol
-
-input_df, stock_symbol = user_input_features()
-
-st.line_chart(input_df.Close)
-st.line_chart(input_df.Volume)
-
-st.write("""
-# Stock Price Prediction
-
-Shown are the stock prediction for next 20 days.
-""")
-
-n_steps = 100
-n_features = 1
-
-model = Sequential()
-model.add(Bidirectional(LSTM(300, activation='relu'), input_shape=(n_steps, n_features)))
-model.add(Dense(1))
-model.compile(optimizer='adam', loss='mse')
-
-model.load_weights(stock_symbol + ".h5")
-df = input_df.dropna(axis=0, how='any', thresh=None, subset=None, inplace=False)
-df = df[df.Volume > 0]
-
-close = df['Close'][-n_steps:].to_list()
-min_in = min(close)
-max_in = max(close)
-in_seq = []
-for i in close :
-  in_seq.append((i - min_in) / (max_in - min_in))
-
-for i in range(20) :
-  x_input = np.array(in_seq[-100:])
-  x_input = x_input.reshape((1, n_steps, n_features))
-  yhat = model.predict(x_input, verbose=0)
-  in_seq.append(yhat[0][0])
-
-norm_res = in_seq[-20:]
-res = []
-for i in norm_res :
-  res.append(i * (max_in - min_in) + min_in)
-
-closepred = close[-80:]
-for x in res :
-  closepred.append(x)
-
-plt.figure(figsize = (20,10))
-plt.plot(closepred, label="Prediction")
-plt.plot(close[-80:], label="Previous")
-plt.ylabel('Price (Rp)', fontsize = 15 )
-plt.xlabel('Days', fontsize = 15 )
-plt.title(stock_symbol + " Stock Prediction", fontsize = 20)
-plt.legend()
-plt.grid()
-
-st.pyplot(plt)