dokucama - network_stuff:machine_learning

jupyter

Anonymous (anonymous@undisclosed.example.com) — 2024-03-30T07:46:41+00:00

python3 -m venv my-jupyter-env source my-jupyter-env/bin/activate pip install jupyter notebook OR pip install jupyterlab * Create a new cell: Esc + B * Run a cell: Ctrl + Enter or Shift + Enter * Change cell type (code/markdown): Esc + Y (code), Esc + M (markdown)

knowledge_graphs

Anonymous (anonymous@undisclosed.example.com) — 2024-03-30T13:33:59+00:00

* graph databases are used to build knowledge graphs. Ontologies Googlge popularized the term. * Eg: neo4j * develop a knowledge graph schema --- Slides *

nns

Anonymous (anonymous@undisclosed.example.com) — 2023-11-02T14:38:15+00:00

NEURONAL NETWORKS Behold the neuron * Keras : Designed to enable fast experimentation with deep neural networks. Keras is built on top of TensorFlow * How the weights are calculated/readjusted: * Backward propagation: If the output is wrong, the system needs to go back and revise its weights

pandas

Anonymous (anonymous@undisclosed.example.com) — 2023-11-02T14:38:15+00:00

* pandas-exercises * labels and data * series and dataframes Link * Series: is one-dimensional. But remember in pandas there's always an index/label axis, so is really two 'columns' * series are like dictionaries but much more powerful (they can be accessed by index/key)

supervised_learning

Anonymous (anonymous@undisclosed.example.com) — 2023-11-02T14:38:15+00:00

SUPERVISED LEARNING: In python, we use the method fit to train a model. Fit~train kmeans.fit(argument) kmeans.predict (argument) # Python predict() predicts the labels of the data values based on the trained model. REGRESSION For continuous tgt values

unsupervised_learning

Anonymous (anonymous@undisclosed.example.com) — 2023-11-02T14:38:15+00:00

UNSUPERVISED LEARNING: In python, we use the method fit to train a model. Fit~train kmeans.fit(argument) kmeans.predict (argument) # ython predict() predicts the labels of the data values based on the trained model.