Commit 2d74ddbc authored by uydqa's avatar uydqa
Browse files


parent 411b055b
......@@ -6,7 +6,7 @@ It consists of three relevant Jupyter-Notebooks:
## 1. `data_exploration.ipynb`
@Anastasia schreib mal hier was pls
Remove high correlated features, extract some features for all columns on 30% of train data, evaluate features for each region, extract most significant features for all regions.
## 2. `Neural.ipynb`
......@@ -23,6 +23,13 @@ Each of the models is trained on a single region of wind turbines.
The models' predictions are combined by using a weighted majority vote.
More specifically, the models' output probabilities are acquired via softmax and averaged to form the ensemble's output.
## 4. `nn_extracted_features.ipynb`
We train a neuronal net to predict the failure with extracted features and the region as a categorical feature.
Furthermore we create a decision tree for region recognition for the training data.
We let the decision three to 'recognize' on of the regions of known data for the 'new' test data.
Finally the neuronal net predict the failure probabilities for the test data with the predicted region as a feature.
## `Others.ipynb`
Data: best features explored in data_exploration.ipynb file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment