#!/usr/bin/env python
# coding: utf-8

# In[1]:


get_ipython().run_line_magic('reload_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')
get_ipython().run_line_magic('matplotlib', 'inline')
import os
os.environ["CUDA_DEVICE_ORDER"]="PCI_BUS_ID";
os.environ["CUDA_VISIBLE_DEVICES"]="0" 
import ktrain
from ktrain import vision as vis


# In[2]:


DATADIR = 'data/planet'
ORIGINAL_DATA = DATADIR+'/train_v2.csv'
CONVERTED_DATA = DATADIR+'/train_v2-CONVERTED.csv'
labels = vis.preprocess_csv(ORIGINAL_DATA, 
                           CONVERTED_DATA, 
                           x_col='image_name', y_col='tags', suffix='.jpg')


# In[3]:


trn, val, preproc = vis.images_from_csv(
                          CONVERTED_DATA,
                         'image_name',
                          directory=DATADIR+'/train-jpg',
                          val_filepath = None,
                          label_columns = labels,
                          data_aug=vis.get_data_aug(horizontal_flip=True, vertical_flip=True))


# In[5]:


model = vis.image_classifier('pretrained_resnet50', trn, val_data=val)
learner = ktrain.get_learner(model, train_data=trn, val_data=val, 
                             batch_size=64, workers=8, use_multiprocessing=False)
learner.freeze(2)


# In[6]:


learner.lr_find()
learner.lr_plot()


# In[9]:


learner.fit_onecycle(1e-4, 20)


# In[10]:


from sklearn.metrics import fbeta_score
import numpy as np
import warnings
def f2(preds, targs, start=0.17, end=0.24, step=0.01):
    with warnings.catch_warnings():
        warnings.simplefilter("ignore")
        return max([fbeta_score(targs, (preds>th), 2, average='samples')
                    for th in np.arange(start,end,step)])


# In[15]:


y_pred = learner.model.predict_generator(val)
y_true = val.labels


# In[16]:


f2(y_pred, y_true)


# In[ ]: