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

# # wetterdienst - A basic notebook example
# 
# pip install wetterdienst

# ## Import modules necessary for general functioning

# In[ ]:


import warnings
warnings.filterwarnings("ignore")

from wetterdienst.provider.dwd.observation import DwdObservationRequest, \
    DwdObservationPeriod, DwdObservationResolution, DwdObservationParameter, DwdObservationDataset

get_ipython().run_line_magic('matplotlib', 'inline')
import matplotlib as mpl
import matplotlib.pyplot as plt
from matplotlib import cm


# Which parameters are available?

# In[ ]:


# all
print("All available parameters")
print(
    DwdObservationRequest.discover()
)
# selection
print("Selection of daily data")
print(
    DwdObservationRequest.discover(
        filter_=DwdObservationResolution.DAILY
    )
)


# ## 1. First check the metadata to inform yourself of available stations
# (here we pick historical daily precipitation - hdp)

# In[ ]:


request = DwdObservationRequest(
    parameter=DwdObservationDataset.PRECIPITATION_MORE,
    resolution=DwdObservationResolution.DAILY,
    period=DwdObservationPeriod.HISTORICAL
)
print("Number of stations with available data: ", request.all().df.sum())
print("Some of the stations:")
request.all().df.head()


# The metadata includes an id, the range of the measurements, the position
# (including height) as well as place and state of it and if it has a file. With the
# following plot we want to show a map of those stations:

# In[ ]:


cmap = cm.get_cmap('viridis')
bounds = request.all().df.height.quantile([0, 0.25, 0.5, 0.75, 1]).values
norm = mpl.colors.BoundaryNorm(bounds, cmap.N)

fig, ax = plt.subplots(figsize=(10, 10))
plot = request.all().df.plot.scatter(
    x="longitude", y="latitude", c="height", cmap=cmap, norm=norm, ax=ax)
plot.set_title("Map of daily precipitation stations in Germany\n"
               "Color refers to height of station")
plt.show()


# ## 2. The usual way of retrieving data

# Let's get some data for the above request

# In[ ]:


print("Receiving historical daily climate data for Dresden-Klotzsche (1048)")
station_data = request.filter_by_station_id(station_id=[1048]).values.all().df

station_data.dropna(axis=0).head()


# See that DATE is already parsed, so we can easily get some nice graphs with matplotlib,
# which we will do in the next part. We can also request direct parameters from the given
# parameter sets. We know that CLIMATE_SUMMARY contains TMK, TNK, TXK and RSK, so let's
# request those. This option will automatically tidy the data.

# In[ ]:


print("Receiving historical daily temperature and precipitation for Dresden-Klotzsche "
      "(1048).")

request = DwdObservationRequest(
    parameter=[
        DwdObservationParameter.DAILY.TEMPERATURE_AIR_200,
        DwdObservationParameter.DAILY.TEMPERATURE_AIR_MAX_200,
        DwdObservationParameter.DAILY.TEMPERATURE_AIR_MIN_200,
        DwdObservationParameter.DAILY.PRECIPITATION_HEIGHT
    ],
    resolution=DwdObservationResolution.DAILY,
    period=DwdObservationPeriod.HISTORICAL
).filter_by_station_id(station_id=(1048, ))

station_data = request.values.all().df

station_data.dropna(axis=0).head()


# ## 3. Let's create some plots
# 
# Now that we have data, let's create some plots! We can create a time series/histogram of
# the temperatures and precipitation

# In[ ]:


cmap = plt.get_cmap('viridis', 4)
colors = cmap.colors

PARAMETERS = ["tnk", "tmk", "txk", "rsk"]

station_data_grouped = station_data.groupby(station_data["parameter"], observed=True)

fig, axes = plt.subplots(nrows=len(PARAMETERS), tight_layout=True, figsize=(10, 40))

for (parameter, group), ax, color in zip(station_data_grouped, axes, colors):
    group.plot(x="date", y="value", label=parameter, alpha=.75, ax=ax, c=color)

plt.tight_layout()
plt.subplots_adjust(top=0.9)
plt.suptitle("Temperature and precipitation time series of Dresden, Germany")

plt.show()


# ## 4. Create yearly values

# In[ ]:


import numpy as np
import pandas as pd
station_data_yearly = []

for (year, parameter), group in station_data.groupby(
        [station_data["date"].dt.year, "parameter"], as_index=False, observed=True):
    if parameter == "rsk":
        station_data_yearly.append(group.dropna().agg({"value": np.sum}))
    else:
        station_data_yearly.append(group.dropna().agg({"value": np.mean}))

station_data_yearly = pd.concat(station_data_yearly)

station_data_yearly


# ## 5. Find a station
# 
# To find a station near to a certain area, call ``filter_by_rank()``.

# In[ ]:


DwdObservationRequest(
    parameter=DwdObservationDataset.CLIMATE_SUMMARY,
    resolution=DwdObservationResolution.DAILY,
    period=DwdObservationPeriod.HISTORICAL,
    start_date="2000-01-01",
    end_date="2010-01-01"
).filter_by_rank(
    51.05089,
    13.73832,
    5
).df