Mahdi Dibaiee
|
8477c02aae
|
fix: use correct order for prediction
|
2019-03-05 15:23:29 +03:30 |
|
Mahdi Dibaiee
|
3dcafddb8c
|
refactor(data): include latitude longitude in columns, not indices
|
2019-03-05 11:29:30 +03:30 |
|
Mahdi Dibaiee
|
865cc775ed
|
fix(nn): better normalization, weight initialization and activation
|
2019-02-28 17:22:50 +03:30 |
|
Mahdi Dibaiee
|
c28fc0850f
|
updates
|
2019-02-28 13:34:47 +03:30 |
|
Mahdi Dibaiee
|
f268e72244
|
feat(temps): various temperatures
|
2019-02-27 15:06:20 +03:30 |
|
Mahdi Dibaiee
|
d8365d6285
|
feat(models): train models and evaluate them
|
2019-02-26 11:50:31 +03:30 |
|
Mahdi Dibaiee
|
0d9a0068b1
|
feat(nn): first model for predicting temp and precip
|
2019-02-20 09:06:03 +03:30 |
|
Mahdi Dibaiee
|
c490f2006b
|
feat(draw): draw dataframe on map
|
2019-02-17 09:50:20 +03:30 |
|
Mahdi Dibaiee
|
a2ff08b195
|
fix(data.py): precipication value was same as temp
|
2019-02-14 12:36:09 +03:30 |
|
Mahdi Dibaiee
|
4318cf71be
|
feat(tf): transform dataframe to tensorflow dataset
|
2019-02-12 08:41:33 +03:30 |
|
Mahdi Dibaiee
|
ef604661ca
|
feat(data): seasonal temp/precip data + distance to water
|
2019-02-11 14:49:14 +03:30 |
|
Mahdi Dibaiee
|
caa1b0443c
|
fix(data.py): optimize for optimal performance and generate data
|
2019-02-08 18:14:57 +03:30 |
|
Mahdi Dibaiee
|
902be97332
|
feat(data.py): data-reading file
|
2019-02-03 09:04:28 +03:30 |
|
Mahdi Dibaiee
|
37d26dba75
|
initial version
|
2019-02-02 16:16:38 +03:30 |
|