## QQplot
plt.figure(figsize=(15,7))
data_points=data.Daily_Discharge
si.stats.probplot(np.log(data_points), dist='norm', plot=plt)
plt.show()
## Boxplot
plt.figure(figsize=(15,7))
plt.boxplot(data.Daily_Discharge,whis=3)
plt.show()
# 2. # Extract rainfall data
token = input('Enter into the token to access to the data: \t') #'lsANjWwoJQegJhKZtKNJPVDGWIGhBSJN'
# the Client object helps you acess the NCDC database with your token
my_client = Client(token, default_units='None', default_limit=1000)
# The extend is the lat, long of the target region.
extent = dict()
Dirs = ['north','south','east','west']
data = input('Enter the extent, format:"N,S,E,W":')
temp = data.split(',')
for i in range(len(Dirs)):
extent[Dirs[i]] = float(temp[i])
# Displaying the dictionary
for key, value in extent.items():
print(str(key)+':'+str(value)) #extent = 41.53,41.21,-84.90,-85.33
# input of start data, end date, type of dataset, and name of gauge
start_date = input('Enter begin date (format:yyyy-mm-dd) \t') # 2019-01-01
Automatically generated by Colaboratory.
Original file is located at
https://colab.research.google.com/drive/1Ck3iB3C0gqZWSQb3VA4glYm_wgM7Gx-T
"""
# vjIpaNKxJbEDODuiQNRXxDujdLHmWbgt
#!pip install cdo-api-py
api_token = "aIILvsLDvkAbPPvZagdxBFTVeemdZEVq"
from cdo_api_py import Client
import pandas as pd
from datetime import datetime
from pprint import pprint # be sure not to share your token publicly
my_client = Client(api_token, default_units=None, default_limit=1000)
extent = {
"north": 37.18,
"south": 25.51,
"east": -92.27,
"west": -111.97,
}
startdate = datetime(1919, 1, 1)
enddate = datetime(2019, 12, 31)
datasetid = 'GSOM'
datatypeid = ['TMIN', 'TMAX', 'PRCP', 'WSF5', 'WSF2']
pprint(my_client.list_datasets())
def filter(self):
# semantic checks on params
# Check (1) exactly four values need to be provided in extent
extent_vals = list(map((lambda val: float(val)),self.extent.split(',')))
if len(extent_vals) != 4:
raise GeoEDFError('NOAAStationFilter requires a N,S,E,W string of floating point numbers as the extent')
# Check (2) that lat and lon pairs are in the right order
north = extent_vals[0]
south = extent_vals[1]
east = extent_vals[2]
west = extent_vals[3]
if south > north:
raise GeoEDFError('please check the ordering of the south and north extents')
if west > east:
raise GeoEDFError('please check the ordering of the east and west extents')
# passed semantic checks, prepare dict of extents for API
extent_dict = {"north": north, "south": south, "east": east, "west": west}
# process dates
try:
startdate = pd.to_datetime(self.start_date,format='%m/%d/%Y')
enddate = pd.to_datetime(self.end_date,format='%m/%d/%Y')
except:
raise GeoEDFError("Error parsing dates provided to NOAAStationFiler, please ensure format is mm/dd/YYYY")
# param checks complete
try:
# get a client for NCDC API usage
cdo_client = Client(self.token, default_units="None", default_limit=1000)
# we are looking for stations with GHCND data
#The find_stations function returns the dataframe containing stations' info within the input extent.
stations = cdo_client.find_stations(
datasetid="GHCND",
extent=extent_dict,
startdate=startdate,
enddate=enddate,
return_dataframe=True)
# filter to only retain stations which have sufficient data for the date range
stations_to_drop = []
# Drop stations without enough observations for the given date range
for i in range(len(stations.maxdate)):
# get max and min date of each station
station_maxdate = pd.to_datetime(stations.maxdate[i],format='%Y-%m-%d')
station_mindate = pd.to_datetime(stations.mindate[i],format='%Y-%m-%d')
# check if station's maxdate is earlier than enddate
if station_maxdate < enddate:
stations_to_drop.append(i)
# check if station's mindate is later than startdate
if station_mindate > startdate:
stations_to_drop.append(i)
# delete stations without enough time length
valid_stations = stations.drop(stations.index[stations_to_drop])
# add station IDs to values array
self.values += list(valid_stations.id)
except:
raise GeoEDFError('Error occurred when querying NCDC API for stations in NOAAStationFiler')
stationid=station['id'],
startdate=startdate,
enddate=enddate,
return_dataframe=True
# include_station_meta=True
)
# Create new DataFrame limiting columns (we don't want ALL of the station data)
columns = ['station', 'date', 'PRCP', 'SNOW']
single = pd.DataFrame(station_data, columns=columns)
# Send to database
single.to_sql(con=db_engine, name='raw_weather',if_exists='append', index=False)
# Connect to DB
conn = connect()
cursor = conn.cursor()
# Get list of stations
cursor.execute('SELECT DISTINCT station_id FROM team')
station_list = [ row[0] for row in cursor.fetchall()]
# Set params for API call
token = '############'
client = Client(token, default_units='metric', default_limit=1000)
for years in range(2008,2013):
get_year_of_data(client, station_list, years)
conn.close()