initial dump

requirements.txt

@@ -0,0 +1,5 @@
+streamlit
+pandas
+numpy
+pandas_datareader
+scikit-learn

streamlitapp.py

@@ -0,0 +1,91 @@
+import streamlit as st
+import pandas as pd
+import numpy as np
+from pandas_datareader import data
+from datetime import date, datetime
+from sklearn.model_selection import train_test_split
+from sklearn.metrics import r2_score
+
+def dateArrange(data):
+    dates = data['Date'].to_list()
+    epochDates = []
+    for i in dates:
+        date_time = np.datetime64(i).astype(datetime)
+        splitDate = date_time.strftime("%Y-%#m-%d").split('-')
+        epochDate = datetime(int(splitDate[0]),int(splitDate[1]),int(splitDate[2]),0,0).timestamp()
+        epochDates.append(epochDate)
+    data['Date'] = epochDates
+
+def dataScraper(ticker):
+    startdate = '2012-01-01'
+    today = date.today().strftime("%Y-%m-%d") 
+    enddate = today
+    try:
+        panel_data = data.DataReader(ticker, 'yahoo', startdate, enddate).reset_index()
+        price_close = panel_data['Adj Close']
+        price_20dma = price_close.rolling(window=20).mean().to_list()[100:] # 20 Day Moving Average
+        price_50dma = price_close.rolling(window=50).mean().to_list()[100:] # 50 day
+        price_100dma = price_close.rolling(window=100).mean().to_list()[100:] # 100 day
+        panel_data = panel_data.iloc[100: , :]
+        panel_data['20dma'] = price_20dma
+        panel_data['50dma'] = price_50dma
+        panel_data['100dma'] = price_100dma
+        dateArrange(panel_data)
+        return panel_data
+    except:
+        print("Error while scraping data")
+        return
+
+def predictor(stock_ticker):
+    prediction_list = []
+    stock_data = dataScraper(stock_ticker)    
+    try:
+        stock_data.iat[0,0]
+    except:
+        print('Error with stock data')
+        return    
+    from sklearn.linear_model import Lasso
+    alpha = 1.0
+    tol = 0.0008
+    max_iter = 10000
+    lasso = Lasso(alpha=alpha, max_iter=max_iter, tol=tol)
+    test_size = 0.1
+    print('\nModel = ' + str(lasso))
+    print('\n~ ' + stock_ticker.upper() + ' Next Day Price Predictions ~\n')
+    X = stock_data.iloc[:-1 , :]
+    y = {
+        'High' : stock_data.iloc[1: , :]['High'], 
+        'Low' : stock_data.iloc[1: , :]['Low'], 
+        'Close (Adjusted)': stock_data.iloc[1: , :]['Close']
+    }
+    sample = stock_data.iloc[-1:, :]
+    for i in y:
+        X_train, X_test, y_train, y_test = train_test_split(X, y[i], test_size=test_size)
+        y_pred_lasso = lasso.fit(np.array(X_train), np.array(y_train))
+        r2_score_lasso = r2_score(np.array(y_test), y_pred_lasso.predict(np.array(X_test)))
+        prediction = y_pred_lasso.predict(np.array(sample))
+        prediction_list.append(prediction)
+        output = "<h5 style='text-align: center; color: #0E7600;'>" + i + ' - ' + str(prediction) + '\n' + "</h1>"
+        st.markdown(output, unsafe_allow_html=True)
+    prediction_list.append(lasso)
+    prediction_list.append(r2_score_lasso)
+    r2score = 'R2 = ' + str(r2_score_lasso)
+    print(r2score)
+
+st.markdown("<h1 style='text-align: center; color: #2BD314;'>Stock Price Predictor v2.0</h1>", unsafe_allow_html=True)
+st.markdown("<h6 style='text-align: center; color: #094B00;'>by Bryan Mildort</h1>", unsafe_allow_html=True)
+ticker = st.text_input('Enter Ticker to Scrape:', placeholder='SPY')
+col1, col2, col3, col4, col5 = st.columns(5)
+with col1:
+    st.write(' ')
+with col2:
+    st.write(' ')
+with col3:
+    if st.button('Scrape!'):
+        predictor(ticker)
+with col4:
+    st.write(' ')
+with col5:
+    st.write(' ')
+
+