Forecasting stock prices using SVR: A timeseries based problem - time-series

Question

I am trying to forecast stock prices (Adj Close) using SVR. I am able to train the model for training data but I'm getting an error for test data. Train data is stored in dataframe df, from 2014 to 2018 and test data is stored in dataframe test_df from 2019 till today. Here is the code:
import pandas as pd
import pandas_datareader.data as web
import datetime
import numpy as np
from matplotlib import style
# Get the stock data using yahoo API:
style.use('ggplot')
# get 2014-2018 data to train our model
start = datetime.datetime(2014,1,1)
end = datetime.datetime(2018,12,30)
df = web.DataReader("TSLA", 'yahoo', start, end)
# get 2019 data to test our model on
start = datetime.datetime(2019,1,1)
end = datetime.date.today()
test_df = web.DataReader("TSLA", 'yahoo', start, end)
# sort by date
df = df.sort_values('Date')
test_df = test_df.sort_values('Date')
# fix the date
df.reset_index(inplace=True)
df.set_index("Date", inplace=True)
test_df.reset_index(inplace=True)
test_df.set_index("Date", inplace=True)
df.tail()
# Converting dates
import matplotlib.dates as mdates
# change the dates into ints for training
dates_df = df.copy()
dates_df = dates_df.reset_index()
# Store the original dates for plotting the predicitons
org_dates = dates_df['Date']
# convert to ints
dates_df['Date'] = dates_df['Date'].map(mdates.date2num)
dates_df.tail()
# Use sklearn support vector regression to predicit our data:
from sklearn.svm import SVR
dates = dates_df['Date'].to_numpy()
prices = df['Adj Close'].to_numpy()
#Convert to 1d Vector
dates = np.reshape(dates, (len(dates), 1))
prices = np.reshape(prices, (len(prices), 1))
svr_rbf = SVR(kernel= 'rbf', C= 1e3, gamma= 0.1)
svr_rbf.fit(dates, prices)
plt.figure(figsize = (12,6))
plt.plot(dates, prices, color= 'black', label= 'Data')
plt.plot(org_dates, svr_rbf.predict(dates), color= 'red', label= 'RBF model')
plt.xlabel('Date')
plt.ylabel('Price')
plt.legend()
plt.show()
For training data it works fine till here. Next, how do I forecast test data (test_df).

Answer 1

Following your convention, it should look as follows:
# change the dates into ints for training
test_dates_df = test_df.copy()
test_dates_df = test_dates_df.reset_index()
# Store the original dates for plotting the predicitons
test_org_dates = test_dates_df['Date']
# convert to ints
test_dates_df['Date'] = test_dates_df['Date'].map(mdates.date2num)
test_dates = test_dates_df['Date'].to_numpy()
test_prices = test_df['Adj Close'].to_numpy()
#Convert to 1d Vector
test_dates = np.reshape(test_dates, (len(test_dates), 1))
test_prices = np.reshape(test_prices, (len(test_prices), 1))
# Predict on unseen test data
y_hat_test = svr_rbf.predict(test_dates)
# Visualize predictions against real values
plt.figure(figsize = (12,6))
plt.plot(test_dates, test_prices, color= 'black', label= 'Data')
plt.plot(test_org_dates, y_hat_test, color= 'red', label= 'RBF model (test)')
plt.xlabel('Date')
plt.ylabel('Price')
plt.legend()
plt.show()