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

# # Multi variable comparison
# Assessing both wave height and wind speed at the same time

# In[1]:


import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from fmskill import ModelResult, PointObservation, TrackObservation, Connector


# In[2]:


get_ipython().run_line_magic('load_ext', 'autoreload')
get_ipython().run_line_magic('autoreload', '2')
get_ipython().run_line_magic('matplotlib', 'inline')


# ## Define observations
# Below, the observations will take the default variable names from the eum type of the item. Alternatively, the user can give another variable name by providing the `variable_name` argument.

# In[3]:


# wave height
o1 = PointObservation('../tests/testdata/SW/HKNA_Hm0.dfs0', item=0, x=4.2420, y=52.6887, name="HKNA_Hm0")
o2 = PointObservation("../tests/testdata/SW/eur_Hm0.dfs0", item=0, x=3.2760, y=51.9990, name="EPL_Hm0")
o3 = TrackObservation("../tests/testdata/SW/Alti_c2_Dutch.dfs0", item=3, name="c2_Hm0")

# wind speed
wind1 = PointObservation('../tests/testdata/SW/HKNA_wind.dfs0', item=0, x=4.2420, y=52.6887, name="HKNA_wind")
wind2 = PointObservation('../tests/testdata/SW/F16_wind.dfs0', item=0, x=4.01222, y=54.1167, name="F16_wind")
wind3 = TrackObservation("../tests/testdata/SW/Alti_c2_Dutch.dfs0", item=2, name="c2_wind")


# In[4]:


o1.variable_name


# ## Define model results
# Two different model results are defined.

# In[5]:


mr1 = ModelResult('../tests/testdata/SW/HKZN_local_2017_DutchCoast.dfsu', name='SW_1')
mr2 = ModelResult('../tests/testdata/SW/HKZN_local_2017_DutchCoast_v2.dfsu', name='SW_2')


# In[6]:


mr1.dfs.items


# ## Connect model and observations and extract
# We connect the observation item and model item by refering to the item name in the ModelResult. Item number can also be used.

# In[7]:


con = Connector()
con.add([o1, o2, o3], [mr1['Sign. Wave Height'], mr2['Sign. Wave Height']])
con.add([wind1, wind2, wind3], [mr1['Wind speed'], mr2['Wind speed']])
con


# In[8]:


cc = con.extract()


# In[9]:


cc.n_variables


# In[10]:


cc.var_names


# ## Analysis
# Now that the result has been extracted, we can do analysis. Multiple variables means an extra level in the multi-index of the skill dataframe. 

# In[11]:


s = cc.skill()
s.round(3)


# In[12]:


s.index.names


# In[13]:


s = cc.skill(variable='Significant_wave_height')
s.style()


# In[14]:


s.sel(observation='c2_Hm0').style(columns='rmse')


# In[15]:


s.plot_line('rmse', ylabel='Hm0 RMSE [m]');


# In[16]:


cc.scatter(model=1)


# ## mean skill
# The `mean_skill()` method will return a weighted average of the skill score per model and variable. You can get the "normal" mean_skill (per model) by selecting a specific variable either by id or name.

# In[17]:


s = cc.mean_skill()
s


# In[18]:


s.plot_bar('si', title='scatter index');


# In[19]:


cc.mean_skill(model='SW_2')


# In[20]:


cc.mean_skill(variable='Significant_wave_height').style(columns=[])


# ## score

# In[21]:


cc.score()


# In[22]:


cc.score(model='SW_1')


# In[23]:


cc.score(variable='Wind_speed')


# In[ ]: