Is there a solution available. I couldn’t find one on Github
Hi @h_dittrich
Me too not able to find a solution for this project by DataQuest. But you can see my work on this Predicting the Stock Market project.
Feedbacks are welcome 
.
Thanks a lot😃. I’ll check it out
1 Like
I took different features because in the text is mentioned not to take the given columns. In the first step I came up with this approach:
get the day_5 col
df[‘day_5’] = df[‘Close’].rolling(window=5).mean().shift(1, axis=0)
get the day_30 col
df[‘day_30’] = df[‘Close’].rolling(window=30).mean().shift(1, axis=0)
get the day_365 col
df[‘day_365’] = df[‘Close’].rolling(window=365).mean().shift(1, axis=0)
features = [‘day_5’, ‘day_30’, ‘day_365’]
and in the second step I added a couple more:
The average volume over the past five days ‘vol_5’ col
df[‘vol_5’] = df[‘Volume’].rolling(window=5).mean().shift(1, axis=0)
The average volume over the past year ‘vol_365’ col
df[‘vol_365’] = df[‘Volume’].rolling(window=365).mean().shift(1, axis=0)
The ratio between the average volume for the past five days,
and the average volume for the past year. ‘vol_ratio’ col
df[‘vol_ratio’] = df[‘vol_5’] / df[‘vol_365’]
features = [‘day_5’, ‘day_30’, ‘day_365’, ‘vol_5’, ‘vol_365’, ‘vol_ratio’]