sim.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import math\n",
    "import numpy as np\n",
    "import scipy.sparse as sp\n",
    "from pmf import PoissonMF\n",
    "import matplotlib.pyplot as plt"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Simulate data\n",
    "\n",
    "Some users, which we call *gaming users*, would like certain notes to appear on the platform, and they coordinate with each other to upvote these notes together.\n",
    "\n",
    "We simulate this scenario as follows:\n",
    "- There are $m=1000$ users and $n=1000$ notes. \n",
    "- $p_{\\text{gaming}}^{\\text{user}}=0.25$ proportion of users are gaming users\n",
    "- Gaming users care about a proportion $p_{\\text{gaming}}^{\\text{item}}=0.1$ of notes\n",
    "\n",
    "The latent factors for a note $i$ are\n",
    "- Let $g_i$ be whether a note is of interest to gaming users: $g_i \\sim \\text{Bern}(p_{\\text{gaming}}^{\\text{item}})$\n",
    "- The item also has other latent factors related to exposure: $\\alpha^{\\text{exp}}_i \\sim \\text{Gamma}_{K-1}(0.3, 0.3)$. The full item latent factor is $\\beta^{\\text{exp}}_i = [g_i, \\alpha_{i1}, \\alpha_{i2}, \\dots, \\alpha_{i(k-1)}]$\n",
    "- The item has latent factors related to the actual observed ratings: $\\theta^{\\text{rating}}_i \\sim \\text{Gamma}_{K}(0.3, 0.3)$\n",
    "\n",
    "The probability $a_{ui}$ that a user $u$ rates a note $i$ is defined by the following:\n",
    "- A gaming user $u$'s probability of rating a note $i$ is $a_{ui} \\sim \\text{Bern}(q \\cdot g_i)$\n",
    "  - $g_i$ is whether a note is of interest to gaming users: $g_i \\sim \\text{Bern}(p_{\\text{gaming}}^{\\text{item}})$\n",
    "  - $q = 0.75$ is how likely a gaming user is to rate a note, given that is a note of interest\n",
    "- A non-gaming user $u$'s probability of rating a note $i$ is $a_{ui} \\sim \\min(\\text{Poisson}(\\theta_u^T \\beta_i), 1)$\n",
    "  - $\\theta_u \\sim \\text{Gamma}_{K}(0.3, 0.3)$ and $\\beta_i \\sim \\text{Gamma}_{K}(0.3, 0.3)$\n",
    "\n",
    "The observed rating $r_{ui}$ is defined by the following:\n",
    "- For a gaming user, $r_{ui} = a_{ui}$ (the gaming users always up-vote the notes of interest to them)\n",
    "- For a non-gaming user, $r_{ui} \\sim \\min(\\text{Poisson}(\\lambda_u^T \\alpha_i)-1, 1)$ \n",
    "  - $\\theta_u \\sim \\text{Gamma}_{K}(0.6, 0.6)$ and $\\beta_i \\sim \\text{Gamma}_{K}(0.6, 0.6)$"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simulate exposure matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Pct ratings (non-gaming users): 0.062908\n",
      "Pct ratings (non-gaming users): 0.07256933333333333\n"
     ]
    }
   ],
   "source": [
    "K = 10 # Num latent factors\n",
    "num_users = 1000\n",
    "num_items = 1000\n",
    "pct_users_gaming = 0.25\n",
    "num_gaming_users = int(num_users * pct_users_gaming)\n",
    "num_normal_users = num_users - num_gaming_users\n",
    "\n",
    "## Generate latent item factors\n",
    "# First, generate whether the item is one that gaming users care about\n",
    "pct_items_gaming_users_care_about = 0.1\n",
    "gamed_item = np.random.binomial(1, pct_items_gaming_users_care_about, size=(num_items, 1))\n",
    "# Then, generate other latent factors\n",
    "item_factors = np.random.gamma(0.3, 0.3, size=(num_items, K))\n",
    "\n",
    "## Exposures for gaming users\n",
    "prob_gaming_user_rates_rel_item = 0.75 # prob a gaming user rates an item they care about\n",
    "probs = (gamed_item*prob_gaming_user_rates_rel_item)[:,0]\n",
    "exposures_gaming = np.random.binomial(\n",
    "    1, probs, \n",
    "    size=(num_gaming_users, num_items))\n",
    "sparsity_gaming = np.sum(exposures_gaming)/num_gaming_users/num_items\n",
    "print(f'Pct ratings (non-gaming users): {sparsity_gaming}')\n",
    "\n",
    "\n",
    "## Exposures for non-gaming users\n",
    "exp_user_factors = np.random.gamma(0.3, 0.3, size=(num_normal_users, K))\n",
    "exp_scores = exp_user_factors @ item_factors.T\n",
    "exposures_nongamimg= np.random.poisson(exp_scores)\n",
    "exposures_nongamimg = np.minimum(exposures_nongamimg, 1)\n",
    "sparsity_nongaming = np.sum(exposures_nongamimg)/num_normal_users/num_items\n",
    "print(f'Pct ratings (non-gaming users): {sparsity_nongaming}')\n",
    "\n",
    "# Combine exposures of gaming and non-gaming users\n",
    "exposures = np.concatenate([exposures_gaming, exposures_nongamimg])"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Simulate ratings matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [],
   "source": [
    "def sigmoid(x):\n",
    "  return 1 / (1 + np.exp(-x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Gamers are upvoting the ones that they rate\n",
    "ratings_gaming = np.ones_like(exposures_gaming)*exposures_gaming\n",
    "# Non-gamers\n",
    "user_factors = np.random.gamma(0.6, 0.6, size=(num_normal_users, K))\n",
    "item_factors = np.random.gamma(0.6, 0.6, size=(num_items, K))\n",
    "ratings_nongaming = user_factors @ item_factors.T\n",
    "ratings_nongaming = np.minimum(np.random.poisson(ratings_nongaming) - 1, 1)\n",
    "ratings_nongaming = ratings_nongaming\n",
    "ratings = np.concatenate([ratings_gaming, ratings_nongaming])\n",
    "ratings_obs = ratings * exposures"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "283092\n",
      "452961\n",
      "263947\n"
     ]
    }
   ],
   "source": [
    "print(np.sum(ratings==-1))\n",
    "print(np.sum(ratings==0))\n",
    "print(np.sum(ratings==1))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "If we just rated notes by the mean of the observed ratings, then the gaming users would be very successful at getting their notes to the top."
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x13a1fbfd0>"
      ]
     },
     "execution_count": 6,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "gt_scores = np.mean(ratings, axis=0)\n",
    "obs_scores = np.mean(ratings_obs, axis=0)\n",
    "gamed_item = gamed_item[:,0]\n",
    "plt.scatter(gt_scores[gamed_item==0], obs_scores[gamed_item==0], color='blue', label='Non-gamed items')\n",
    "plt.scatter(gt_scores[gamed_item==1], obs_scores[gamed_item==1], color='red', label='Gamed items')\n",
    "plt.xlabel('Ground-truth note scores')\n",
    "plt.ylabel('Observed note scores')\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# Fit model"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fit PMF to exposure matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<style>#sk-container-id-1 {\n",
       "  /* Definition of color scheme common for light and dark mode */\n",
       "  --sklearn-color-text: black;\n",
       "  --sklearn-color-line: gray;\n",
       "  /* Definition of color scheme for unfitted estimators */\n",
       "  --sklearn-color-unfitted-level-0: #fff5e6;\n",
       "  --sklearn-color-unfitted-level-1: #f6e4d2;\n",
       "  --sklearn-color-unfitted-level-2: #ffe0b3;\n",
       "  --sklearn-color-unfitted-level-3: chocolate;\n",
       "  /* Definition of color scheme for fitted estimators */\n",
       "  --sklearn-color-fitted-level-0: #f0f8ff;\n",
       "  --sklearn-color-fitted-level-1: #d4ebff;\n",
       "  --sklearn-color-fitted-level-2: #b3dbfd;\n",
       "  --sklearn-color-fitted-level-3: cornflowerblue;\n",
       "\n",
       "  /* Specific color for light theme */\n",
       "  --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, white)));\n",
       "  --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, black)));\n",
       "  --sklearn-color-icon: #696969;\n",
       "\n",
       "  @media (prefers-color-scheme: dark) {\n",
       "    /* Redefinition of color scheme for dark theme */\n",
       "    --sklearn-color-text-on-default-background: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-background: var(--sg-background-color, var(--theme-background, var(--jp-layout-color0, #111)));\n",
       "    --sklearn-color-border-box: var(--sg-text-color, var(--theme-code-foreground, var(--jp-content-font-color1, white)));\n",
       "    --sklearn-color-icon: #878787;\n",
       "  }\n",
       "}\n",
       "\n",
       "#sk-container-id-1 {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 pre {\n",
       "  padding: 0;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-hidden--visually {\n",
       "  border: 0;\n",
       "  clip: rect(1px 1px 1px 1px);\n",
       "  clip: rect(1px, 1px, 1px, 1px);\n",
       "  height: 1px;\n",
       "  margin: -1px;\n",
       "  overflow: hidden;\n",
       "  padding: 0;\n",
       "  position: absolute;\n",
       "  width: 1px;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-dashed-wrapped {\n",
       "  border: 1px dashed var(--sklearn-color-line);\n",
       "  margin: 0 0.4em 0.5em 0.4em;\n",
       "  box-sizing: border-box;\n",
       "  padding-bottom: 0.4em;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-container {\n",
       "  /* jupyter's `normalize.less` sets `[hidden] { display: none; }`\n",
       "     but bootstrap.min.css set `[hidden] { display: none !important; }`\n",
       "     so we also need the `!important` here to be able to override the\n",
       "     default hidden behavior on the sphinx rendered scikit-learn.org.\n",
       "     See: https://github.com/scikit-learn/scikit-learn/issues/21755 */\n",
       "  display: inline-block !important;\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-text-repr-fallback {\n",
       "  display: none;\n",
       "}\n",
       "\n",
       "div.sk-parallel-item,\n",
       "div.sk-serial,\n",
       "div.sk-item {\n",
       "  /* draw centered vertical line to link estimators */\n",
       "  background-image: linear-gradient(var(--sklearn-color-text-on-default-background), var(--sklearn-color-text-on-default-background));\n",
       "  background-size: 2px 100%;\n",
       "  background-repeat: no-repeat;\n",
       "  background-position: center center;\n",
       "}\n",
       "\n",
       "/* Parallel-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item::after {\n",
       "  content: \"\";\n",
       "  width: 100%;\n",
       "  border-bottom: 2px solid var(--sklearn-color-text-on-default-background);\n",
       "  flex-grow: 1;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel {\n",
       "  display: flex;\n",
       "  align-items: stretch;\n",
       "  justify-content: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  position: relative;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:first-child::after {\n",
       "  align-self: flex-end;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:last-child::after {\n",
       "  align-self: flex-start;\n",
       "  width: 50%;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-parallel-item:only-child::after {\n",
       "  width: 0;\n",
       "}\n",
       "\n",
       "/* Serial-specific style estimator block */\n",
       "\n",
       "#sk-container-id-1 div.sk-serial {\n",
       "  display: flex;\n",
       "  flex-direction: column;\n",
       "  align-items: center;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  padding-right: 1em;\n",
       "  padding-left: 1em;\n",
       "}\n",
       "\n",
       "\n",
       "/* Toggleable style: style used for estimator/Pipeline/ColumnTransformer box that is\n",
       "clickable and can be expanded/collapsed.\n",
       "- Pipeline and ColumnTransformer use this feature and define the default style\n",
       "- Estimators will overwrite some part of the style using the `sk-estimator` class\n",
       "*/\n",
       "\n",
       "/* Pipeline and ColumnTransformer style (default) */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable {\n",
       "  /* Default theme specific background. It is overwritten whether we have a\n",
       "  specific estimator or a Pipeline/ColumnTransformer */\n",
       "  background-color: var(--sklearn-color-background);\n",
       "}\n",
       "\n",
       "/* Toggleable label */\n",
       "#sk-container-id-1 label.sk-toggleable__label {\n",
       "  cursor: pointer;\n",
       "  display: block;\n",
       "  width: 100%;\n",
       "  margin-bottom: 0;\n",
       "  padding: 0.5em;\n",
       "  box-sizing: border-box;\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:before {\n",
       "  /* Arrow on the left of the label */\n",
       "  content: \"▸\";\n",
       "  float: left;\n",
       "  margin-right: 0.25em;\n",
       "  color: var(--sklearn-color-icon);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 label.sk-toggleable__label-arrow:hover:before {\n",
       "  color: var(--sklearn-color-text);\n",
       "}\n",
       "\n",
       "/* Toggleable content - dropdown */\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content {\n",
       "  max-height: 0;\n",
       "  max-width: 0;\n",
       "  overflow: hidden;\n",
       "  text-align: left;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content pre {\n",
       "  margin: 0.2em;\n",
       "  border-radius: 0.25em;\n",
       "  color: var(--sklearn-color-text);\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-toggleable__content.fitted pre {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~div.sk-toggleable__content {\n",
       "  /* Expand drop-down */\n",
       "  max-height: 200px;\n",
       "  max-width: 100%;\n",
       "  overflow: auto;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {\n",
       "  content: \"▾\";\n",
       "}\n",
       "\n",
       "/* Pipeline/ColumnTransformer-specific style */\n",
       "\n",
       "#sk-container-id-1 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator-specific style */\n",
       "\n",
       "/* Colorize estimator box */\n",
       "#sk-container-id-1 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted input.sk-toggleable__control:checked~label.sk-toggleable__label {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label label.sk-toggleable__label,\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  /* The background is the default theme color */\n",
       "  color: var(--sklearn-color-text-on-default-background);\n",
       "}\n",
       "\n",
       "/* On hover, darken the color of the background */\n",
       "#sk-container-id-1 div.sk-label:hover label.sk-toggleable__label {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "/* Label box, darken color on hover, fitted */\n",
       "#sk-container-id-1 div.sk-label.fitted:hover label.sk-toggleable__label.fitted {\n",
       "  color: var(--sklearn-color-text);\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Estimator label */\n",
       "\n",
       "#sk-container-id-1 div.sk-label label {\n",
       "  font-family: monospace;\n",
       "  font-weight: bold;\n",
       "  display: inline-block;\n",
       "  line-height: 1.2em;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-label-container {\n",
       "  text-align: center;\n",
       "}\n",
       "\n",
       "/* Estimator-specific */\n",
       "#sk-container-id-1 div.sk-estimator {\n",
       "  font-family: monospace;\n",
       "  border: 1px dotted var(--sklearn-color-border-box);\n",
       "  border-radius: 0.25em;\n",
       "  box-sizing: border-box;\n",
       "  margin-bottom: 0.5em;\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-0);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-0);\n",
       "}\n",
       "\n",
       "/* on hover */\n",
       "#sk-container-id-1 div.sk-estimator:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-2);\n",
       "}\n",
       "\n",
       "#sk-container-id-1 div.sk-estimator.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-2);\n",
       "}\n",
       "\n",
       "/* Specification for estimator info (e.g. \"i\" and \"?\") */\n",
       "\n",
       "/* Common style for \"i\" and \"?\" */\n",
       "\n",
       ".sk-estimator-doc-link,\n",
       "a:link.sk-estimator-doc-link,\n",
       "a:visited.sk-estimator-doc-link {\n",
       "  float: right;\n",
       "  font-size: smaller;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1em;\n",
       "  height: 1em;\n",
       "  width: 1em;\n",
       "  text-decoration: none !important;\n",
       "  margin-left: 1ex;\n",
       "  /* unfitted */\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted,\n",
       "a:link.sk-estimator-doc-link.fitted,\n",
       "a:visited.sk-estimator-doc-link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "div.sk-estimator:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link:hover,\n",
       ".sk-estimator-doc-link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "div.sk-estimator.fitted:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover,\n",
       "div.sk-label-container:hover .sk-estimator-doc-link.fitted:hover,\n",
       ".sk-estimator-doc-link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "/* Span, style for the box shown on hovering the info icon */\n",
       ".sk-estimator-doc-link span {\n",
       "  display: none;\n",
       "  z-index: 9999;\n",
       "  position: relative;\n",
       "  font-weight: normal;\n",
       "  right: .2ex;\n",
       "  padding: .5ex;\n",
       "  margin: .5ex;\n",
       "  width: min-content;\n",
       "  min-width: 20ex;\n",
       "  max-width: 50ex;\n",
       "  color: var(--sklearn-color-text);\n",
       "  box-shadow: 2pt 2pt 4pt #999;\n",
       "  /* unfitted */\n",
       "  background: var(--sklearn-color-unfitted-level-0);\n",
       "  border: .5pt solid var(--sklearn-color-unfitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link.fitted span {\n",
       "  /* fitted */\n",
       "  background: var(--sklearn-color-fitted-level-0);\n",
       "  border: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "\n",
       ".sk-estimator-doc-link:hover span {\n",
       "  display: block;\n",
       "}\n",
       "\n",
       "/* \"?\"-specific style due to the `<a>` HTML tag */\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link {\n",
       "  float: right;\n",
       "  font-size: 1rem;\n",
       "  line-height: 1em;\n",
       "  font-family: monospace;\n",
       "  background-color: var(--sklearn-color-background);\n",
       "  border-radius: 1rem;\n",
       "  height: 1rem;\n",
       "  width: 1rem;\n",
       "  text-decoration: none;\n",
       "  /* unfitted */\n",
       "  color: var(--sklearn-color-unfitted-level-1);\n",
       "  border: var(--sklearn-color-unfitted-level-1) 1pt solid;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted {\n",
       "  /* fitted */\n",
       "  border: var(--sklearn-color-fitted-level-1) 1pt solid;\n",
       "  color: var(--sklearn-color-fitted-level-1);\n",
       "}\n",
       "\n",
       "/* On hover */\n",
       "#sk-container-id-1 a.estimator_doc_link:hover {\n",
       "  /* unfitted */\n",
       "  background-color: var(--sklearn-color-unfitted-level-3);\n",
       "  color: var(--sklearn-color-background);\n",
       "  text-decoration: none;\n",
       "}\n",
       "\n",
       "#sk-container-id-1 a.estimator_doc_link.fitted:hover {\n",
       "  /* fitted */\n",
       "  background-color: var(--sklearn-color-fitted-level-3);\n",
       "}\n",
       "</style><div id=\"sk-container-id-1\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>PoissonMF(n_components=2, random_state=1, verbose=True)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator  sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-1\" type=\"checkbox\" checked><label for=\"sk-estimator-id-1\" class=\"sk-toggleable__label  sk-toggleable__label-arrow \">&nbsp;PoissonMF<span class=\"sk-estimator-doc-link \">i<span>Not fitted</span></span></label><div class=\"sk-toggleable__content \"><pre>PoissonMF(n_components=2, random_state=1, verbose=True)</pre></div> </div></div></div></div>"
      ],
      "text/plain": [
       "PoissonMF(n_components=2, random_state=1, verbose=True)"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "exposures_scr = sp.csr_matrix(exposures)\n",
    "user_ids, item_ids = exposures_scr.nonzero()\n",
    "pmf = PoissonMF(n_components=2, random_state=1, verbose=True, a=0.3, b=0.3, c=0.3, d=0.3)\n",
    "pmf.fit(exposures_scr, user_ids, item_ids)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Latent representations learned by Poisson MF\n",
    "pmf_user_factors, pmf_item_factors = pmf.Eb, pmf.Et.T"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "[1.2378687  0.00421149]\n",
      "[0.05246881 0.07119092]\n"
     ]
    }
   ],
   "source": [
    "gaming_users = pmf_user_factors[:num_gaming_users]\n",
    "non_gaming_users = pmf_item_factors[num_gaming_users:]\n",
    "print(gaming_users.mean(axis=0))\n",
    "print(non_gaming_users.mean(axis=0))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "Text(0.5, 1.0, 'Latent representations of users learned by Poisson MF')"
      ]
     },
     "execution_count": 10,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(gaming_users[:, 0], gaming_users[:, 1], label='Gaming users')\n",
    "plt.scatter(non_gaming_users[:, 0], non_gaming_users[:, 1], label='Non-gaming users')\n",
    "plt.legend()\n",
    "plt.title('Latent representations of users learned by Poisson MF')"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Fit MF to ratings matrix"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [],
   "source": [
    "%load_ext autoreload\n",
    "import torch\n",
    "import torch.optim as optim\n",
    "from torch.utils.data import Dataset, DataLoader\n",
    "from torch import nn\n",
    "from mf import MatrixFactorizationModel, ModelData"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "# Our full model that deconfounds with the substitute confounder from step 1a\n",
    "deconf_mf_model = MatrixFactorizationModel(\n",
    "    num_users, num_items, \n",
    "    exp_user_factors=pmf_user_factors, exp_item_factors=pmf_item_factors,\n",
    "    n_components=4)\n",
    "\n",
    "# Regular matrix factorization without deconfounding\n",
    "mf_model = MatrixFactorizationModel(num_users, num_items, n_components=4)\n",
    "\n",
    "rating_labels = ratings_obs[user_ids, item_ids]\n",
    "rating_tensor = torch.FloatTensor(rating_labels).to(deconf_mf_model.device)\n",
    "user_idxs_tensor = torch.LongTensor(user_ids).to(deconf_mf_model.device)\n",
    "note_idxs_tensor = torch.LongTensor(item_ids).to(deconf_mf_model.device)\n",
    "exp_tensor = torch.ones_like(rating_tensor).to(deconf_mf_model.device)\n",
    "\n",
    "data = ModelData(rating_tensor, user_idxs_tensor, note_idxs_tensor, exp_tensor)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0: train L2-reg loss = 0.387, val L2-reg loss = 0.745\n",
      "Epoch 0: train MSE = 0.743, val MSE = 0.742\n",
      "Epoch 20: train L2-reg loss = 0.231, val L2-reg loss = 0.527\n",
      "Epoch 20: train MSE = 0.386, val MSE = 0.491\n",
      "Epoch 40: train L2-reg loss = 0.221, val L2-reg loss = 0.524\n",
      "Epoch 40: train MSE = 0.370, val MSE = 0.488\n",
      "Epoch 60: train L2-reg loss = 0.219, val L2-reg loss = 0.524\n",
      "Epoch 60: train MSE = 0.367, val MSE = 0.488\n",
      "Epoch 80: train L2-reg loss = 0.219, val L2-reg loss = 0.524\n",
      "Epoch 80: train MSE = 0.366, val MSE = 0.489\n",
      "Epoch 100: train L2-reg loss = 0.218, val L2-reg loss = 0.524\n",
      "Epoch 100: train MSE = 0.365, val MSE = 0.488\n",
      "Epoch 120: train L2-reg loss = 0.218, val L2-reg loss = 0.523\n",
      "Epoch 120: train MSE = 0.364, val MSE = 0.488\n",
      "Epoch 140: train L2-reg loss = 0.218, val L2-reg loss = 0.523\n",
      "Epoch 140: train MSE = 0.364, val MSE = 0.487\n"
     ]
    }
   ],
   "source": [
    "train_loss, val_loss = deconf_mf_model.fit(data, epochs=150, lr=0.1, print_interval=20, validate_fraction=0.1, print_loss=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 0: train L2-reg loss = 0.387, val L2-reg loss = 0.746\n",
      "Epoch 0: train MSE = 0.744, val MSE = 0.744\n",
      "Epoch 20: train L2-reg loss = 0.262, val L2-reg loss = 0.514\n",
      "Epoch 20: train MSE = 0.432, val MSE = 0.493\n",
      "Epoch 40: train L2-reg loss = 0.256, val L2-reg loss = 0.508\n",
      "Epoch 40: train MSE = 0.430, val MSE = 0.488\n",
      "Epoch 60: train L2-reg loss = 0.256, val L2-reg loss = 0.505\n",
      "Epoch 60: train MSE = 0.428, val MSE = 0.485\n",
      "Epoch 80: train L2-reg loss = 0.255, val L2-reg loss = 0.507\n",
      "Epoch 80: train MSE = 0.428, val MSE = 0.487\n",
      "Epoch 100: train L2-reg loss = 0.255, val L2-reg loss = 0.506\n",
      "Epoch 100: train MSE = 0.428, val MSE = 0.486\n",
      "Epoch 120: train L2-reg loss = 0.255, val L2-reg loss = 0.506\n",
      "Epoch 120: train MSE = 0.428, val MSE = 0.487\n",
      "Epoch 140: train L2-reg loss = 0.255, val L2-reg loss = 0.506\n",
      "Epoch 140: train MSE = 0.428, val MSE = 0.486\n"
     ]
    }
   ],
   "source": [
    "train_loss, val_loss = mf_model.fit(data, epochs=150, lr=0.1, print_interval=20, validate_fraction=0.1, print_loss=True)"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "## Voting aggregation"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {},
   "outputs": [],
   "source": [
    "note_scores = mf_model.get_vote_scores(torch.mean)\n",
    "deconf_note_scores = deconf_mf_model.get_vote_scores(torch.mean)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x140f13c70>"
      ]
     },
     "execution_count": 16,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(gt_scores[gamed_item==0], note_scores[gamed_item==0], color='blue', label='Non-gamed items')\n",
    "plt.scatter(gt_scores[gamed_item==1], note_scores[gamed_item==1], color='red', label='Gamed items')\n",
    "plt.xlabel('Ground-truth note scores')\n",
    "plt.ylabel('Regular MF note scores')\n",
    "plt.legend()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "<matplotlib.legend.Legend at 0x142eb7c10>"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    },
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plt.scatter(gt_scores[gamed_item==0], deconf_note_scores[gamed_item==0], color='blue', label='Non-gamed items')\n",
    "plt.scatter(gt_scores[gamed_item==1], deconf_note_scores[gamed_item==1], color='red', label='Gamed items')\n",
    "plt.xlabel('Ground-truth note scores')\n",
    "plt.ylabel('Deconfounder note scores')\n",
    "plt.legend()"
   ]
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}