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

# In[1]:


import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import datetime as dt
from salishsea_tools import evaltools as et

get_ipython().run_line_magic('matplotlib', 'inline')


# In[2]:


ls '/ocean/ksuchy/MOAD/observe/Data and Code files for KS 2020dec11/2020_05_21 1995-2011 SoG VNH.csv'


# In[3]:


df=pd.read_csv('/ocean/ksuchy/MOAD/observe/Data and Code files for KS 2020dec11/2020_05_21 2012-2015 SoG VNH.csv',
               encoding = "ISO-8859-1")


# In[4]:


df


# In[5]:


df.keys()


# In[6]:


df['Biomass(mg/m3)']


# In[7]:


df['Date'][0],df['STN_TIME'][0]


# In[8]:


df['Date'][1000:1020]


# In[9]:


df['Date'][0].split('/')


# In[10]:


dateslist=list()


# In[11]:


for el in df['Date']:
    dateslist.append(el.split('/'))


# In[12]:


timeslist=list()
for el in df['STN_TIME']:
    timeslist.append(el.split(':'))


# In[13]:


dts=list()
for ii,jj in zip(dateslist,timeslist):
    dts.append(dt.datetime(int(ii[2]),int(ii[0]),int(ii[1]),int(jj[0]),int(jj[1])))


# In[14]:


df.loc[df.Twilight=='Daylight']['STN_TIME'].unique()


# In[15]:


df['dtUTC']=et.pac_to_utc(dts) #convert from Pac time to UTC


# In[16]:


df['Order:'].unique()


# In[17]:


colList=('Amphipoda', 'Decapoda','Euphausiacea', 'Calanoida', 'Cyclopoida', 
    'Poecilostomatoida','Copelata','Harpacticoida',)


# In[18]:


df.keys()


# In[19]:


dtsutc=et.pac_to_utc(dts)


# In[20]:


df.loc[0]


# In[21]:


towIDlist=['Key', 'region_name', 'Station',  'lon', 'lat', 'dtUTC', 'Twilight', 'Net_Type', 'Mesh_Size(um)', 'DEPTH_STRT1', 'DEPTH_END1', 'Bottom Depth(m)']


# In[22]:


towIDlist2=['Key', 'region_name', 'Station',  'lon', 'lat', 'dtUTC', 'Twilight', 'Net_Type', 'Mesh_Size(um)', 'DEPTH_STRT1', 'DEPTH_END1', 'Bottom Depth(m)','CTD']


# In[23]:


len(df.groupby(towIDlist)),len(df.groupby(towIDlist2)),len(df.groupby(['Key']))


# In[24]:


# Key is a unique identifier for each tow
# do not group by CTD due to NaN values


# In[25]:


biomassDF=df.groupby(towIDlist,as_index=False).first()\
     .loc[:,towIDlist].copy(deep=True)


# In[26]:


biomassDF


# In[27]:


def getbiomass(colname,key,origdf):
    biomassArray=df.loc[(origdf.Key==key)&(origdf['Order:']==colname),
                    ['Biomass(mg/m3)']]
    biomass=np.nansum(biomassArray)
    return biomass


# In[28]:


for icol in colList:
    biomassDF[icol]=[getbiomass(icol,ikey,df) for ikey in biomassDF['Key']]


# In[29]:


biomassDF


# In[30]:


import netCDF4 as nc


# In[31]:


ftemp=nc.Dataset('/data/eolson/results/MEOPAR/NEMO-forcing-new/grid/mesh_mask201702.nc')


# In[32]:


ftemp.variables.keys()


# In[33]:


ftemp.variables['e3t_0']


# In[34]:


ftemp.variables['e3t_1d'][:]


# In[35]:


fdict={'ptrc_T':1,'grid_T':1}
start_date = dt.datetime(2015,6,1)
end_date = dt.datetime(2015,6,30)
flen=1 # number of days per model output file. always 1 for 201905 and 201812 model runs
namfmt='nowcast' # for 201905 and 201812 model runs, this should always be 'nowcast'
# filemap is dictionary of the form variableName: fileType, where variableName is the name
# of the variable you want to extract and fileType designates the type of 
# model output file it can be found in (usually ptrc_T for biology, grid_T for temperature and 
# salinity)
filemap={'microzooplankton':'ptrc_T','mesozooplankton':'ptrc_T'}
# fdict is a dictionary mappy file type to its time resolution. Here, 1 means hourly output
# (1h file) and 24 means daily output (1d file). In certain runs, multiple time resolutions 
# are available
fdict={'ptrc_T':1,'grid_T':1}


# In[36]:


PATH= '/results2/SalishSea/nowcast-green.201905/'


# In[37]:


biomassDF.rename(columns={'lon':'Lon','lat':'Lat'},inplace=True)


# In[38]:


biomassDF.keys()


# In[39]:


biomassDF.rename(columns={'DEPTH_STRT1':'Z_lower','DEPTH_END1':'Z_upper','Bottom Depth (m)': 'Z'},inplace=True)


# In[40]:


data=et.matchData(biomassDF,filemap,fdict,start_date,end_date,'nowcast',PATH,1,quiet=False,method='vertNet');


# In[41]:


data


# In[ ]: