model 1 – linear regression
r2: 0.1566089012155698
rmse: 1.8625218879551908
coefficients:
SentimentTitle      -0.383499
SentimentHeadline   -0.064708
DaysSinceEpoch      -0.000678
Topic_microsoft      0.101848
Topic_obama          1.779152
Topic_palestine      0.023738
dtype: float64
model 2 – random forest on raw ts
r2: 0.7441325592979975
rmse: 0.8661035218490399
top importances:
TS50                 0.810814
SentimentHeadline    0.099992
SentimentTitle       0.067386
TS49                 0.001883
TS48                 0.000589
TS15                 0.000503
TS18                 0.000503
TS13                 0.000498
TS24                 0.000498
TS10                 0.000480
dtype: float64
model 3 – random forest on pca(ts)
r2: 0.7442278904925559
rmse: 0.8659421602173341
pca variance explained (first 10): [9.38529911e-01 3.24317512e-02 1.76049987e-02 7.50439628e-03
 1.90148973e-03 6.83679307e-04 3.57135169e-04 2.12058930e-04
 1.33577763e-04 9.66846072e-05]
total variance explained: 0.9994556829781833
model 4 – logistic regression (viral vs non-viral)
threshold (shares): 214.0
accuracy: 0.7287481626653601
f1 (positive class): 0.35709101466105386
roc auc: 0.7530964866530827
confusion matrix:
 [[10669  4023]
 [  406  1230]]
model 5 – kmeans on ts shapes
silhouette score: 0.9732852082508215
         count         mean  median     max
cluster                                    
0         4978    36.751708     3.0  7045.0
1            1  1886.000000  1886.0  1886.0
2           21  2477.761905  1291.0  8010.0
cluster centroid summary:
    cluster       avg_ts          ts1         ts10         ts25         ts50
0        0     8.317766     0.297710     2.959221     7.836079    17.221977
1        1  1885.920000  1885.000000  1886.000000  1886.000000  1886.000000
2        2   640.917143    22.761905   211.142857   579.047619  1387.619048