# I need a hint on how to start developing a new `.ipynb` project for Jupyter Notebook on Time Series with a specific demands

I’m looking for Stock Price Time Series Forecasting using Deep Convolutional/fully connected Networks/RNN code for forecasting the prices on stock markets using Python. The simplest possible code for this task with `.ipynb` extension will do.

I cannot find one with google, any hints for downloading or creating it on my own ?

EDIT More specifically, I need from data with one or more times series-a daily data with prices, and my input how many days from now
on
and my probability input I need lower and upper bound how much will the asset cost after this period: estimated min and max value. Or, in other words
I need to compose the optimal portfolio
for these assets, leaving some money without buying anything: how much fraction of the initial amount of money should be intact on my account, among how much % shopuld I dedicate to n-th asset.

EDIT
Example:
say, I have this 2 time series:

[1,2,4,3,2,2,2]

[3,3,3,3,4,4,8]

and 100\$ with initial amount

should yield this (by now just random, in reality that should make a sense and be derived from the 2 assets by statistical means and Deep Learning) probabilities:

31\$ of asset 1,
49\$ of asset 2,
20\$ leaving on my account after 4 days, all happening with probability 8%.

Is there such a code .ipynb at best already available ?