https://github.com/lim-calculus/sequence-time-seires-and-predictions

My Solution to DeepLearning.AI TensorFlow Developer Certificate Course 4 : Sequence, Time Seires and Predictions
https://github.com/lim-calculus/sequence-time-seires-and-predictions

Last synced: over 1 year ago
JSON representation

My Solution to DeepLearning.AI TensorFlow Developer Certificate Course 4 : Sequence, Time Seires and Predictions

• Host: GitHub
• URL: https://github.com/lim-calculus/sequence-time-seires-and-predictions
• Owner: Lim-Calculus
• Created: 2023-01-14T23:49:43.000Z (over 3 years ago)
• Default Branch: main
• Last Pushed: 2023-01-25T03:19:50.000Z (over 3 years ago)
• Last Synced: 2025-01-22T00:34:12.081Z (over 1 year ago)
• Language: Jupyter Notebook
• Size: 3.39 MB
• Stars: 0
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md

Awesome Lists containing this project

README

          
# Sequence-Time-Seires-and-Predictions

My Solution to DeepLearning.AI TensorFlow Developer Certificate Course 4 : Sequence, Time Seires and Predictions

# Week 1

## Time Series

- Time Series typically defined as an ordered sequence of values that are usually equally spaced overtime

- Univariate Time Series : a single value at each time step

![Univariate Time Series](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_Univariate_Time_Series.png)

- Multivariate Time Series : time series that have multiple values at each time step 

![Multivariate Time Series](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_Multivariate_Time_Series.png)

- Imputation :  In statistics, imputation is the process of replacing missing data with substituted values. When substituting for a data point, it is known as "unit imputation"; when substituting for a component of a data point, it is known as "item imputation"

![Imputation in Moore's Law](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_Moore'sLaw_ImputedData.png)

![Week1_ImputedData.png](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_ImputedData.png)

## Common Pattern in Time Series

- Trend : Where time series have a specific direction that they are moving (Example : Moore's Law)

- Seasonality : pattern repeat at predictable intervals

![Week1_Seasonality.png](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_Seasonality.png)

- White noise : random value

- Autocorrelation :  it correlates with a delayed copy of itself often called a lag

![Week1_Autocorrelation.png](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_Autocorrelation.png)

## Train, Val, Test

- Splitting the time series into training, validation and test period

![Week1_TrainValTest.png](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_TrainValTest.png)

## Metrics FOr Evaluating Performance

![Week1_MetricsForEvaluatingPerformance.png](https://github.com/Lim-Calculus/Sequence-Time-Seires-and-Predictions/blob/main/Images/Week1_MetricsForEvaluatingPerformance.png)

# Week 3 - Recurrent Neural Network in Time Series Predictions

## Recurrent Neural Network : A recurrent neural network (RNN) is a special type of artificial neural network adapted to work for time series data or data that involves sequences.