RobertTLange

import tweepy
import os
from typing import List, Optional


class TwitterClient:
    def __init__(
        self,
        consumer_key: str,
        consumer_secret: str,

RobertTLange

import jax
import jax.numpy as jnp

def ou_process(key, steps, dt, mu, tau, sigma):
    """ Generate an Ornstein-Uhlenbeck process sample. """
    ou_init = jnp.zeros((steps + 1, ))
    noise = jax.random.normal(key, (steps,))
    def ou_step(t, val):
        dx = (-(val[t-1]-mu)/tau * dt 
              + sigma*jnp.sqrt(2/tau)*

RobertTLange

def binary_cross_entropy(y_true, y_pred):
    y_true = np.append(1 - y_true, y_true, axis=1)
    y_pred = np.append(1 - y_pred, y_pred, axis=1)
    bce = -(y_true * np.log(y_pred)).sum(axis=1)
    return bce

RobertTLange

def train_logistic_regression(n, d, n_epoch, batch_size, b_init, l_rate):
    # Generate the data for a coefficient vector & init progress tracker!
    data_loader = DataLoader(n, d, batch_size, binary=True)
    b_hist, func_val_hist, param_error, acc_hist = [], [], [], []

    # Get the coefficients as solution to optimized sklearn function
    logreg = LogisticRegression(penalty='none', solver='lbfgs', multi_class='multinomial')
    logreg.fit(data_loader.X, data_loader.y)
    norm_coeff = np.linalg.norm(logreg.coef_.ravel())

RobertTLange

import numpy as np
from sklearn.linear_model import LogisticRegression

class DataLoader(object):
    # Small class object for dual number - Two real numbers (real & dual part)
    def __init__(self, n, d, batch_size, binary=False):
        self.total_dim = d + 1
        self.X, self.y = self.generate_regression_data(n, d, binary)

        # Set batch_id for different indices