aus10powell

SELECT 
  transaction_date, 
  AVG(transaction_amount) AS rolling_avg
FROM (
  SELECT 
    DATE_TRUNC('day', transaction_time) AS transaction_date, 
    SUM(transaction_amount) AS transaction_amount
  FROM 
    transactions

aus10powell

#####################
# 2x2 Contingency table w/ test
#####################


import stats

d = {
    "flagged": [221, 221],
    "not-flagged": [2,10],

aus10powell

aus10powell

import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.nn import functional as F

class TextCNN(nn.Module):
    def __init__(self, batch_size, output_size, in_channels, out_channels, kernel_heights,
                 stride, padding, keep_probab, vocab_size, embedding_dim, weights):
        super(TextCNN, self).__init__()

aus10powell

import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.nn import functional as F

class TextCNN(nn.Module):
    def __init__(self, batch_size, output_size, in_channels, out_channels, kernel_heights,
                 stride, padding, keep_probab, vocab_size, embedding_dim, weights):
        super(TextCNN, self).__init__()

aus10powell

import torch
import torch.nn as nn
from torch.autograd import Variable
from torch.nn import functional as F

class TextCNN(nn.Module):
    def __init__(self, batch_size, output_size, in_channels, out_channels, kernel_heights,
                 stride, padding, keep_probab, vocab_size, embedding_dim, weights):

aus10powell

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 28,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [