samcarlos

import numpy as np
import pandas as pd
from sklearn.ensemble import RandomForestRegressor
from ds_projects.lift_model.erupt import get_erupts_curves_aupc

def get_simple_uplift_data(num_obs):
    """Creates sample uplift dataset with 3 variables.
    First two variables are of form y_i = x_i*t + e for two responses
    Thrid response is just noise

samcarlos

import numpy as np
from sklearn.linear_model import LinearRegression
from sklearn.ensemble import RandomForestRegressor

num_obs = 1000

t = np.random.binomial(1, .5, num_obs)
x = np.random.binomial(1, .5, num_obs)
y = 10 + 2*t*x - t + np.random.normal(0, .1, num_obs)

samcarlos

import numpy as np
import pandas as pd
import random


def weighted_avg_and_std(values, weights):
    """computes weighted averages and stdevs
    Args:
        values (np.array): variable of interest
        weight (np.array): weight to assign each observation

samcarlos

import numpy as np
import pandas as pd

from keras import backend as K
from keras.layers import Input, Dense, Dropout
from keras.models import Model
from keras.wrappers.scikit_learn import KerasRegressor

from sklearn.metrics import make_scorer
from sklearn.model_selection import GridSearchCV

samcarlos

library(dplyr)
library(genlasso)

d <- data.frame(x = sample(-seq(-20,20,2), 1e5, replace = TRUE)) %>%
  mutate(event_rate = abs(round((x)/2)/10),
         y = rbinom(n(), 1, event_rate),
         x_fctr = as.factor(x))


y <- d$y