Happiness narratives
Data Discrepancies
There's more data used for the hedometer evaluation than there is for the ml training and evaluat...
Results
SVR Joy
MSE: 0.9964795758847595 Mean Absolute Error 0.8209001542496819 R2: -0.0969678363700448 Pea...
SVM Joy
MSE: 0.6431352807865082 Mean Absolute Error 0.6158711064947314 R2: 0.2920088534366445 Pear...
Lasso Joy
MSE: 1.0281566480572382 Mean Absolute Error 0.8358763189438444 R2: -0.1318393281341672 Pea...
Lasso Sadness
SE: 0.9307384965022848 Mean Absolute Error 0.7960851914177507 R2: -0.04084814009093862 Pea...
SVR Sadness
SE: 0.9454209231533085 Mean Absolute Error 0.8007222131105772 R2: -0.05726754954823532 Pea...
SVM Sadness
MSE: 0.6640974977269949 Mean Absolute Error 0.6386105570026086 R2: 0.2573374283476926 Pear...
Correlation
Binyan was doing pearson's correlation. Thinks maybe we should do spearman
Neural Networks
RELU unscaled results
Joy train on 9 folds, test on 1 2020-05-13 12:15:50,734 - INFO - allennlp.common.util - Metrics:...
Linear Unscaled results
Joy lr = 0.001 Really bad, mean absolute error of 1.3ish at the end. lr = 0.0001 Seemed to ov...
RNN scaled results
3 hid lr 0.00001 2020-05-14 22:57:02,171 - INFO - allennlp.common.util - Metrics: { "best_ep...
RNN unscaled results
Glove embeddings 64 dimensional RNN 1 hidden layer 2 hidden layers 0.0001 lr 2020-05-19 23:1...