conormm

conormm

library(lme4)
library(tidyverse)
library(broom)

data(sleepstudy, package='lme4')
df <- sleepstudy %>% as_data_frame()
df$Days <- scale(df$Days)
df
getwd()
setwd("/Users/conormcdonald/Desktop/")

conormm

model = MoonsModel(n_features=2, n_neurons=50)

cost_func = nn.BCELoss()
optimizer = tr.optim.Adam(params=model.parameters(), lr=0.01)

num_epochs = 20

losses = []
accs = []
for e in range(num_epochs):

conormm

class MoonsModel(nn.Module):
    def __init__(self, n_features, n_neurons):
        super(MoonsModel, self).__init__()
        self.hidden = nn.Linear(in_features=n_features, out_features=n_neurons)
        self.out_layer = nn.Linear(in_features=n_neurons, out_features=2)

    def forward(self, X):
        out = F.relu(self.hidden(X))
        out = F.sigmoid(self.out_layer(out))
        return out

conormm

class PrepareData(Dataset):

    def __init__(self, X, y):
        if not torch.is_tensor(X):
            self.X = torch.from_numpy(X)
        if not torch.is_tensor(y):
            self.y = torch.from_numpy(y)

    def __len__(self):
        return len(self.X)

conormm

from sklearn.datasets import make_moons
import pandas as pd
import numpy as np

import torch
from torch.autograd import Variable
import torch.nn as nn
from torch.utils.data import Dataset, DataLoader
import torch.nn.functional as F

conormm

import pandas as pd
import numpy as np
import os
import pymc3 as pm
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt

%matplotlib inline

df = pd.read_csv("sleep_study.csv")

conormm

import pandas as pd
import numpy as np
import os
import pymc3 as pm
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt

df = pd.read_csv("sleep_study.csv")
df.columns = df.columns.str.lower()
dayscaler = StandardScaler()

conormm

from sklearn.datasets import make_moons
import torch as tr
from torch.autograd import Variable
import torch.nn as nn
import matplotlib.pyplot as plt
import numpy as np
from keras.utils import np_utils

%matplotlib inline

conormm

# inspired by these tweets:

#The idea is very simple. You want to compare two groups' outcomes on some metric y. 
#But the two groups are quite different in their covariates X. 
#One approach is to predict y given X using a random forest, 
#saving the proximity matrix. This i,jth entry in this matrix is the
#proportion of terminal nodes shared by observations i and j. 
#That is, "how similar" they are in some random forest space. 
#Now, for each person in group B, select the corresponding person in group A that is nearest in this this space. 
#And compute your differences on this subset