Skip to content
Time series prediction with Sequential Model and LSTM units
Branch: master
Clone or download
Pull request Compare This branch is even with gcarq:master.
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
data
.gitignore
LICENSE
README.md
international-airline-passengers.csv
main.py
requirements.txt

README.md

Time series predictions with Keras

Requirements

  • Theano
  • Keras
  • matplotlib
  • pandas
  • scikit-learn
  • tqdm
  • numpy

Usage

git clone https://github.com/gcarq/keras-timeseries-prediction.git
cd keras-timeseries-prediction/
pip install -r requirements.txt
python main.py

Dataset

The dataset is international-airline-passengers.csv which contains 144 data points ranging from Jan 1949 to Dec 1960. Each data point represents monthly passengers in thousands.

Dataset

Model

model = Sequential()
model.add(LSTM(64,
               activation='relu',
               batch_input_shape=(batch_size, look_back, 1),
               stateful=True,
               return_sequences=False))
model.add(Dense(1, activation='linear'))
model.compile(loss='mean_squared_error', optimizer='adam')

Results

Predictions

You can’t perform that action at this time.