Gain insights into time series analysis using Python. Explore pandas and NumPy for data manipulation, visualize trends, learn ARIMA modeling, and employ machine learning for forecasting.

tarball.tar.gz

time_series

This course is an introduction to time series data analysis and forecasting with Python. Time series data is prevalent in many fields, including finance, economics, and meteorology. In this course, you will learn how to use Python's popular pandas and NumPy libraries to manipulate, visualize, and analyze time series data.

The course covers topics such as time series decomposition, stationary and non-stationary data, autocorrelation and partial autocorrelation, and modeling techniques like ARIMA. You will learn how to implement these techniques in Python and how to use them to make forecasts. Moreover, you will also be introduced to some advanced techniques including machine learning algorithms.

By the end of the course, you will have a solid understanding of time series data analysis and forecasting with Python. You will be able to import, clean, and manipulate time series data, use statistical modeling techniques to make forecasts, and apply machine learning algorithms to time series data.

Time Series Analysis with Python

An LSTM has more layers than a generic neural network.

An LSTM has feedback connections, meaning that each node can also use its output from the past as input for the present.

In an LSTM, layers are interconnected. Whereas in a generic neural network, layers are isolated from each other. 

What is the main difference between a generic neural network and an LSTM?

What is the main difference between a generic neural network and an LSTM?

`model.add_country_holidays(country_name='US')`

How are national holidays in the United States added in Prophet?

How are national holidays in the United States added in Prophet?

The number of features to be used in the LSTM layer.

The number of observations to be used for fitting the model.

What does the `100` stand for in the line of code below?

`model.add(LSTM(100, input_shape=(1, lags)))`

What does the <code>100</code> stand for in the line of code below?
<code>model.add(LSTM(100, input_shape=(1, lags)))</code>

How many forecasts are generated each point in time in the block of code below?
 
    mod, samples = analysis(
        passengers,
        family="poisson",
        forecast_start=forecast_start,
        forecast_end=forecast_end,
        k=10,
        nsamps=100,
        prior_length=3,
        rho=.9,
        deltrend=0.5,
        delregn=0.9
    )

How many forecasts are generated each point in time in the block of code below?
<pre><code>mod, samples = analysis(
 passengers,
 family=&quot;poisson&quot;,
 forecast_start=forecast_start,
 forecast_end=forecast_end,
 k=10,
 nsamps=100,
 prior_length=3,
 rho=.9,
 deltrend=0.5,
 delregn=0.9
)</code></pre>

In Prophet, how should the "date" and "target variable" columns be named, respectively?

In Prophet, how should the “date” and “target variable” columns be named, respectively?

Check your understanding of "Advanced Time Series Forecasting."

Introduction to Time Series

Python Basics for Time Series

Time Series Analysis

Basic Time Series Forecasting

Advanced Time Series Forecasting

Forecast Evaluation

Time Series Analysis and Forecasting

Practical Examples

Final Project

Conclusion

Quiz: Advanced Time Series Forecasting