sergeyf

# -*- coding: utf-8 -*-
"""
Created on Tue Jul 21 07:44:21 2020

@author: serge
"""

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns

sergeyf

import numpy as np
from sklearn.impute import MICEImputer
from sklearn.datasets import load_boston
from sklearn.ensemble import RandomForestRegressor
from sklearn.pipeline import Pipeline
from sklearn.model_selection import cross_val_score

import matplotlib.pyplot as plt
import seaborn as sns
sns.set(context='poster')

sergeyf

:: Install choco .exe and add choco to PATH
@powershell -NoProfile -ExecutionPolicy Bypass -Command "iex ((New-Object System.Net.WebClient).DownloadString('https://chocolatey.org/install.ps1'))" && SET "PATH=%PATH%;%ALLUSERSPROFILE%\chocolatey\bin"

:: for ease of updating
choco install ChocolateyGUI -fy

:: basics
choco install googlechrome -fy
choco install agentransack -fy
choco install vlc -fy

sergeyf

'''
References: 
    https://medium.com/teconomics-blog/using-ml-to-resolve-experiments-faster-bd8053ff602e
    https://insightr.wordpress.com/2017/06/28/cross-fitting-double-machine-learning-estimator/
    https://arxiv.org/pdf/1608.00060.pdf
'''

import numpy as np

from sklearn.linear_model import LassoCV, LinearRegression, BayesianRidge, LogisticRegression

sergeyf

import numpy as np

# the function
def f_of_x(X, w):
    n,d = X.shape
    X_dot_w = np.dot(X,w)
    y = np.zeros(n)
    # the inner product randomly goes through a sin
    # or a cos
    cos_flag = np.random.randn(n) < 0.0

sergeyf

import matplotlib.pyplot as plt
import numpy as np
import seaborn

from keras.layers import Input, Dense, merge, ELU, Dropout
from keras.models import Model
from keras.regularizers import l2
from keras import backend as K
from keras.optimizers import rmsprop, adam

sergeyf

import numpy as np

def f_of_x(X,w):
    n,d = X.shape
    X_dot_w = np.dot(X,w)
    y = np.zeros(n)
    # the inner product goes through a sin
    # or a cos, depending on simple condition
    cos_flag = X[:,0] < 0.0
    sin_flag = ~cos_flag

sergeyf

import numpy as np
from scipy.spatial.distance import pdist, squareform

# function that converts categorical variable 
# into a one-hot encoding
def one_hot_encoding(x):
    n = len(x)    
    min_category = np.min(x)
    max_category = np.max(x)
    num_categories = max_category - min_category + 1

sergeyf

'''
Based on: https://gist.github.com/bshillingford/6259986edca707ca58dd
Modified to work on Windows by: Sergey Feldman
Jan 17, 2016

Requirements: pdflatex, bibtex
'''

import requests
import lxml.html as html

sergeyf

import numpy as np

class Data_generator(object):
    
    def __init__(self,K,d,reward_type='binary'):
        
        self.d = d # dimension of the feature vector
        self.K = K # number of bandits
        self.reward_type = reward_type