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

# In[1]:


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


# In[2]:


from __future__ import print_function
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# import seaborn as sns
# sns.set_style('whitegrid')

from IPython.display import HTML


# In[3]:


flowdata = pd.read_pickle("./data/FlowData")
raindata = pd.read_pickle("./data/RainData")


# # Hydropy-package
# 
# Go to the [hydropy website](http://stijnvanhoey.github.io/hydropy/) for more information on the package and the code on Github.

# In[4]:


#Loading the hydropy package
import hydropy as hp


# We have a Dataframe with river discharge at different locations in the Maarkebeek basin (Belgium):

# In[5]:


HTML('<iframe src=http://biomath.ugent.be/~stvhoey/maarkebeek_data/ width=700 height=350></iframe>')


# Data downloaded from http://www.waterinfo.be/, made available by the Flemish Environmental Agency (VMM).

# In[6]:


flowdata.head()


# In[7]:


flowdata.tail()


# In[8]:


print(len(flowdata), 'records', 'from', flowdata.index[0], 'till', flowdata.index[-1])


# Converting the dataframe to a hydropy time series datatype, provides extra functionalities:

# In[9]:


myflowserie = hp.HydroAnalysis(flowdata)


# ### Select the summer of 2009:

# In[10]:


myflowserie.get_year('2009').get_season('summer').plot(figsize=(12,6))


# ### Select only the recession periods of the discharges (catchment drying) in June 2011:

# In[11]:


myflowserie.get_year('2011').get_month("Jun").get_recess().plot(figsize=(12,6))


# ### Peak values above the 90th percentile for the station LS06_347 in July 2010:

# In[12]:


fig, ax = plt.subplots(figsize=(13, 6))
myflowserie['LS06_347'].get_year('2010').get_month("Jul").get_highpeaks(150, above_percentile=0.9).plot(style='o', ax=ax)
myflowserie['LS06_347'].get_year('2010').get_month("Jul").plot(ax=ax)


# ## Select storms and make plot

# In[13]:


raindata.columns


# In[14]:


storms = myflowserie.derive_storms(raindata['P05_019'], 'LS06_347',
                                   number_of_storms=3, drywindow=50,
                                   makeplot=True)


# In[15]:


storms = myflowserie.derive_storms(raindata['P06_014'], 'LS06_347',
                                   number_of_storms=3, drywindow=96,
                                   makeplot=True)


# ## Season averages (Pandas!)

# In[16]:


myflowserie.data.groupby('season').mean()


# ## Goals

# * Use the power of Python **Pandas**
# * Provide **domain specific** (hydrological) functionalities
# * Provide **intuitive** interface for hydrological time series (main focus on flow series)
# * Combine different earlier written loose functionalities in **package**
# * Independent, but useful in global **Phd**-developed framework: enables the user to quickly look at different properties of model behaviour

# ## Where?

# * Code : https://github.com/stijnvanhoey/hydropy -->  **Fork** and contribute
# * Website : https://stijnvanhoey.github.io/hydropy/

# ### How to start?
# 1. Fork the github repo
# 2. Get the code on your computer
# 
#         git clone https://github.com/yourname/hydropy
# 3. Run the python setup script (install as development package):
# 
#         python setup.py develop
# 4. Improve implementation, add functionalities,...
#     
#     * Make a new branch
#     * Make improvements on this branch
#     * push the branch towards the repo and perform a pull request

# In[ ]:





# ## Functionalities extended

# In[17]:


import hydropy as hp
flowdata = pd.read_pickle("./data/FlowData")
raindata = pd.read_pickle("./data/RainData")
myflowserie = hp.HydroAnalysis(flowdata)


# ### Forwarding Pandas functionalities

# In[18]:


# Data inspection
myflowserie.summary() #head(), tail(),


# In[19]:


# Resampling frequencies
temp1 = myflowserie.frequency_resample('7D', 'mean')  # 7 day means
temp1.head()


# In[20]:


temp2 = myflowserie.frequency_resample("M", "max")  # Monthly maxima
temp2.head()


# In[21]:


temp3 = myflowserie.frequency_resample("A", 'sum')  # Yearly sums
temp3.head(6)


# In[22]:


#slicing of the dataframes
myflowserie['L06_347']['2009'].plot()


# ### Easy period selection

# In[23]:


# get_month, get_year, get_season, get_date_range
myflowserie.get_date_range("01/01/2010","03/05/2010").plot(figsize=(13, 6))


# In[24]:


# or combine different statements:
myflowserie.get_year('2010').get_month(6).plot(figsize=(13, 6))


# For the seasons some options are available: Meteorologic (first of the month) or astrologic (21st of the month)

# In[25]:


myflowserie.current_season_dates()


# In[26]:


myflowserie.info_season_dates('north', 'astro')


# ### 'Hydrological' selections

# In[27]:


# Peaks (high or low)
myflowserie['LS06_348'].get_year('2012').get_highpeaks(60, above_percentile=0.8).data.dropna().head()


# In[28]:


# Recessions and climbing periods  get_recess, get_climbing
myflowserie.get_year("2012").get_month("april").get_climbing().plot(figsize=(13, 6))


# In[29]:


# above/below certain percentile values
myflowserie["LS06_347"].get_above_percentile(0.6).get_year('2011').get_season('summer').plot()


# Furthermore:
# 
# * get_storms_per_year (in combination with rain-data)
# * get_above_baseflow (in combination with baseflow-data) => next on the list
# * ...

# In[ ]:





# In[ ]: