gvyshnya

# COVID-19 case study

# import packages
import pandas as pd
import pdpipe as pdp
import numpy as np

from sklearn import preprocessing
import time
from datetime import datetime

gvyshnya

import numpy as np
	import pandas as pd
	import pdpipe as pdp
	
	# ... data reading code goes here
	
	# set up a transformation pipeline
    pipeline_1 = pdp.ApplyByCols(
        ['lat', 'lon', 'lat_inspection_location', 'lon_inspection_location'],
        lambda col: pd.to_numeric(col)

gvyshnya

# GBM prediction

import numpy as np
import pandas as pd
from sklearn import *
import datetime as dt

def RMSLE(y, pred):
    return metrics.mean_squared_error(y, pred) ** 0.5

gvyshnya

# GBM prediction

import numpy as np
import pandas as pd
from sklearn import *
import datetime as dt

def RMSLE(y, pred):
    return metrics.mean_squared_error(y, pred) ** 0.5

gvyshnya

def sparsity_ratio(X):
    return 1.0 - np.count_nonzero(X) / float(X.shape[0] * X.shape[1])
print("input sparsity ratio:", sparsity_ratio(X))

gvyshnya

# Project/Contest: Recruit Restaurant Visitor Forecasting (https://www.kaggle.com/c/recruit-restaurant-visitor-forecasting)
#
# Summary: this is a basic pre-processing and feature engineering script to transform original input data from the Customer
#          into a ready-for modelling training and testing sets
#
# inspirations:
# - https://www.kaggle.com/the1owl/surprise-me/

import numpy as np
import pandas as pd

gvyshnya

#!/usr/bin/python
import pandas as pd
import numpy as np
import fbprophet as fbpro
import sklearn.metrics as skm
import math
import datetime as dt


class ProphetModeller(object):

gvyshnya

import xgboost as xgb
import numpy as np
from sklearn.datasets import load_digits
from sklearn.cross_validation import train_test_split

rng = np.random.RandomState(1994)

digits = load_digits(2)
X = digits['data']
y = digits['target']

gvyshnya

# Improve ensemble configuration
$ vi code/config.R

# Commit all the changes.
$ git commit -am "Updated weights of the models in the ensemble"

# Reproduce the ensemble prediction
$ dvc repro data/submission_ensemble.csv

gvyshnya

# Project/Competition: https://www.kaggle.com/c/web-traffic-time-series-forecasting/
# Simple benchmark prediction with median (median by page, weekdays, and holidays)
#
# - You should insall Workalendar from its github repo directly
# >>> pip install git+https://github.com/novafloss/workalendar.git


import pandas as pd
import pandas.tseries.holiday as hol
import re