Newer
Older
{
"cells": [
{
"cell_type": "markdown",
"metadata": {
"toc": true
},
"source": [
"<h1>Table of Contents<span class=\"tocSkip\"></span></h1>\n",
"<div class=\"toc\"><ul class=\"toc-item\"><li><span><a href=\"#Causal-model\" data-toc-modified-id=\"Causal-model-1\"><span class=\"toc-item-num\">1 </span>Causal model</a></span><ul class=\"toc-item\"><li><span><a href=\"#Notes\" data-toc-modified-id=\"Notes-1.1\"><span class=\"toc-item-num\">1.1 </span>Notes</a></span></li></ul></li><li><span><a href=\"#Data-sets\" data-toc-modified-id=\"Data-sets-2\"><span class=\"toc-item-num\">2 </span>Data sets</a></span><ul class=\"toc-item\"><li><span><a href=\"#Synthetic-data-with-unobservables\" data-toc-modified-id=\"Synthetic-data-with-unobservables-2.1\"><span class=\"toc-item-num\">2.1 </span>Synthetic data with unobservables</a></span></li><li><span><a href=\"#Data-without-unobservables\" data-toc-modified-id=\"Data-without-unobservables-2.2\"><span class=\"toc-item-num\">2.2 </span>Data without unobservables</a></span></li></ul></li><li><span><a href=\"#Algorithms\" data-toc-modified-id=\"Algorithms-3\"><span class=\"toc-item-num\">3 </span>Algorithms</a></span><ul class=\"toc-item\"><li><span><a href=\"#Contraction-algorithm\" data-toc-modified-id=\"Contraction-algorithm-3.1\"><span class=\"toc-item-num\">3.1 </span>Contraction algorithm</a></span></li><li><span><a href=\"#Causal-approach---metrics\" data-toc-modified-id=\"Causal-approach---metrics-3.2\"><span class=\"toc-item-num\">3.2 </span>Causal approach - metrics</a></span></li></ul></li><li><span><a href=\"#Performance-comparison\" data-toc-modified-id=\"Performance-comparison-4\"><span class=\"toc-item-num\">4 </span>Performance comparison</a></span><ul class=\"toc-item\"><li><span><a href=\"#With-unobservables-in-the-data\" data-toc-modified-id=\"With-unobservables-in-the-data-4.1\"><span class=\"toc-item-num\">4.1 </span>With unobservables in the data</a></span></li><li><span><a href=\"#Without-unobservables\" data-toc-modified-id=\"Without-unobservables-4.2\"><span class=\"toc-item-num\">4.2 </span>Without unobservables</a></span></li></ul></li></ul></div>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Causal model\n",
"\n",
"Our model is defined by the probabilistic expression \n",
"\n",
"P(Y=0 | \\text{do}(R=r)) = \\sum_x \\underbrace{P(Y=0|X=x, T=1)}_\\text{1} \n",
"\\overbrace{P(T=1|R=r, X=x)}^\\text{2} \n",
"\\underbrace{P(X=x)}_\\text{3}\n",
"\\end{equation}\n",
"\n",
"which is equal to \n",
"\n",
"\\begin{equation}\\label{model_cont}\n",
"P(Y=0 | \\text{do}(R=r)) = \\int_x P(Y=0|X=x, T=1)P(T=1|R=r, X=x)P(X=x)\n",
"\\end{equation}\n",
"\n",
"for continuous $x$. In the model Z is a latent, unobserved variable, and can be excluded from the expression with do-calculus by showing that $X$ is admissible for adjustment. Model as a graph:\n",
"![Model as picture](../figures/intervention_model.png \"Intervention model\")\n",
"\n",
"For predicting the probability of negative outcome the following should hold because by Pearl $P(Y=0 | \\text{do}(R=r), X=x) = P(Y=0 | R=r, X=x)$ when $X$ is an admissible set:\n",
"\n",
"\\begin{equation} \\label{model_pred}\n",
"P(Y=0 | \\text{do}(R=r), X=x) = P(Y=0|X=x, T=1)P(T=1|R=r, X=x).\n",
"\\end{equation}\n",
"\n",
"Still it should be noted that this prediction takes into account the probability of the individual to be given a positive decision ($T=1$), see second term in \\ref{model_pred}.\n",
"\n",
"----\n",
"\n",
"### Notes\n",
"\n",
"* Equations \\ref{model_disc} and \\ref{model_cont} describe the whole causal effect in the population (the causal effect of changing $r$ over all strata $X$).\n",
"* Prediction should be possible with \\ref{model_pred}. Both terms can be learned from the data. NB: the probability $P(Y=0 | \\text{do}(R=r), X=x)$ is lowest when the individual $x$ is the most dangerous or the least dangerous. How could we infer/predict the counterfactual \"what is the probability of $Y=0$ if we were to let this individual go?\" has yet to be calculated.\n",
"* Is the effect of R learned/estimated correctly if it is just plugged in to a predictive model (e.g. logistic regression)? **NO**\n",
"* $P(Y=0 | do(R=0)) = 0$ only in this application. <!-- My predictive models say that when $r=0$ the probability $P(Y=0) \\approx 0.027$ which would be a natural estimate in another application/scenario (e.g. in medicine the probability of an adverse event when a stronger medicine is distributed to everyone. Then the probability will be close to zero but not exactly zero.) -->"
"metadata": {},
"outputs": [],
"source": [
"# Imports\n",
"\n",
"import numpy as np\n",
"import pandas as pd\n",
"from datetime import datetime\n",
"import matplotlib.pyplot as plt\n",
"import scipy.stats as scs\n",
"import scipy.integrate as si\n",
"import seaborn as sns\n",
"import numpy.random as npr\n",
"from sklearn.preprocessing import OneHotEncoder\n",
"from sklearn.linear_model import LogisticRegression\n",
"from sklearn.ensemble import RandomForestClassifier\n",
"from sklearn.model_selection import train_test_split\n",
"\n",
"# Settings\n",
"\n",
"%matplotlib inline\n",
"\n",
"plt.rcParams.update({'font.size': 16})\n",
"plt.rcParams.update({'figure.figsize': (14, 7)})\n",
"\n",
"# Suppress deprecation warnings.\n",
"\n",
"import warnings\n",
"\n",
"def fxn():\n",
" warnings.warn(\"deprecated\", DeprecationWarning)\n",
"\n",
"with warnings.catch_warnings():\n",
" warnings.simplefilter(\"ignore\")\n",
" fxn()"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Data sets\n",
"\n",
"### Synthetic data with unobservables\n",
"\n",
"In the chunk below, we generate the synthetic data as described by Lakkaraju et al. The default values and definitions of $Y$ and $T$ values follow their description.\n",
"\n",
"**Parameters**\n",
"\n",
"* M = `nJudges_M`, number of judges\n",
"* N = `nSubjects_N`, number of subjects assigned to each judge\n",
"* betas $\\beta_i$ = `beta_i`, where $i \\in \\{X, Z, W\\}$ are coefficients for the respected variables\n",
"\n",
"**Columns of the data:**\n",
"\n",
"* `judgeID_J` = judge IDs as running numbering from 0 to `nJudges_M - 1`\n",
"* R = `acceptanceRate_R`, acceptance rates\n",
"* X = `X`, invidual's features observable to all (models and judges)\n",
"* Z = `Z`, information observable for judges only\n",
"* W = `W`, unobservable / inaccessible information\n",
"* T = `decision_T`, bail-or-jail decisions where $T=0$ represents jail decision and $T=1$ bail decision.\n",
"* Y = `result_Y`, result variable, if $Y=0$ person will or would recidivate and if $Y=1$ person will or would not commit a crime.\n",
"\n",
"The generated data will have M\\*N rows."
"outputs": [
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>result_Y</th>\n",
" <th>0.0</th>\n",
" <th>1.0</th>\n",
" <th>All</th>\n",
" </tr>\n",
" <tr>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>17426</td>\n",
" <td>7579</td>\n",
" <td>25005</td>\n",
" <td>7525</td>\n",
" <td>17470</td>\n",
" <td>24995</td>\n",
" <td>24951</td>\n",
" <td>25049</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"0 17426 7579 25005\n",
"1 7525 17470 24995\n",
"All 24951 25049 50000"
"def sigmoid(x):\n",
" return 1 / (1 + np.exp(-x))\n",
"def generateData(nJudges_M=100,\n",
" nSubjects_N=500,\n",
" beta_X=1.0,\n",
" beta_Z=1.0,\n",
" beta_W=0.2):\n",
"\n",
" # Assign judge IDs as running numbering from 0 to nJudges_M - 1\n",
" judgeID_J = np.repeat(range(0, nJudges_M), nSubjects_N)\n",
"\n",
" # Sample acceptance rates uniformly from a closed interval\n",
" # from 0.1 to 0.9 and round to tenth decimal place.\n",
" acceptance_rates = np.round(npr.uniform(.1, .9, nJudges_M), 10)\n",
"\n",
" # Replicate the rates so they can be attached to the corresponding judge ID.\n",
" acceptanceRate_R = np.repeat(acceptance_rates, nSubjects_N)\n",
"\n",
" # Sample the variables from standard Gaussian distributions.\n",
" X = npr.normal(size=nJudges_M * nSubjects_N)\n",
" Z = npr.normal(size=nJudges_M * nSubjects_N)\n",
" W = npr.normal(size=nJudges_M * nSubjects_N)\n",
"\n",
" probabilities_Y = sigmoid(beta_X * X + beta_Z * Z + beta_W * W)\n",
"\n",
" # 0 if P(Y = 0| X = x; Z = z; W = w) >= 0.5 , 1 otherwise\n",
" result_Y = 1 - probabilities_Y.round()\n",
" # For the conditional probabilities of T we add noise ~ N(0, 0.1)\n",
" probabilities_T += npr.normal(0, np.sqrt(0.1), nJudges_M * nSubjects_N)\n",
"\n",
" # Initialize decision values as 1\n",
" decision_T = np.ones(nJudges_M * nSubjects_N)\n",
"\n",
" # Initialize the dataframe\n",
" df_init = pd.DataFrame(np.column_stack(\n",
" (judgeID_J, acceptanceRate_R, X, Z, W, result_Y, probabilities_T,\n",
" decision_T)),\n",
" columns=[\n",
" \"judgeID_J\", \"acceptanceRate_R\", \"X\", \"Z\", \"W\",\n",
" \"result_Y\", \"probabilities_T\", \"decision_T\"\n",
" ])\n",
"\n",
" # Sort by judges then probabilities in decreasing order\n",
" data = df_init.sort_values(by=[\"judgeID_J\", \"probabilities_T\"],\n",
" ascending=False)\n",
"\n",
" # Iterate over the data. Subject is in the top (1-r)*100% if\n",
" # his within-judge-index is over acceptance threshold times\n",
" # the number of subjects assigned to each judge. If subject\n",
" # is over the limit they are assigned a zero, else one.\n",
" data.reset_index(drop=True, inplace=True)\n",
"\n",
" data['decision_T'] = np.where(\n",
" (data.index.values % nSubjects_N) <\n",
" ((1 - data['acceptanceRate_R']) * nSubjects_N), 0, 1)\n",
"\n",
" # Halve the data set to test and train\n",
" train, test = train_test_split(data, test_size=0.5)\n",
" train_labeled = train.copy()\n",
" test_labeled = test.copy()\n",
" # Set results as NA if decision is negative.\n",
" train_labeled.loc[train_labeled.decision_T == 0, 'result_Y'] = np.nan\n",
" test_labeled.loc[test_labeled.decision_T == 0, 'result_Y'] = np.nan\n",
" return train_labeled, train, test_labeled, test, data"
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### Data without unobservables\n",
"\n",
"In the chunk below, we generate a simplified data. The default values and definitions of $Y$ and $T$ values follow the previous description.\n",
"\n",
"**Parameters**\n",
"\n",
"* M = `nJudges_M`, number of judges\n",
"* N = `nSubjects_N`, number of subjects assigned to each judge\n",
"* betas $\\beta_i$ = `beta_i`, where $i \\in \\{X, Z, W\\}$ are coefficients for the respected variables\n",
"\n",
"**Columns of the data:**\n",
"\n",
"* `judgeID_J` = judge IDs as running numbering from 0 to `nJudges_M - 1`\n",
"* R = `acceptanceRate_R`, acceptance rates\n",
"* X = `X`, invidual's features observable to all (models and judges), now $X \\sim \\mathcal{N}(0, 1)$\n",
"* T = `decision_T`, bail-or-jail decisions where $T=0$ represents jail decision and $T=1$ bail decision.\n",
"* $p_y$ = `probabilities_Y`, variable where $p_y = P(Y=1)$\n",
"* Y = `result_Y`, result variable, if $Y=0$ person will or would recidivate and if $Y=1$ person will or would not commit a crime. Here $Y \\sim \\text{Bernoulli}(1/exp(\\beta_X \\cdot X))$"
]
},
{
"cell_type": "code",
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
]
},
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>result_Y</th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>All</th>\n",
" </tr>\n",
" <tr>\n",
" <th>decision_T</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>9421</td>\n",
" <td>16546</td>\n",
" <td>25967</td>\n",
" <td>15589</td>\n",
" <td>8444</td>\n",
" <td>24033</td>\n",
" <td>25010</td>\n",
" <td>24990</td>\n",
" <td>50000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"result_Y 0 1 All\n",
"decision_T \n",
"0 9421 16546 25967\n",
"1 15589 8444 24033\n",
"All 25010 24990 50000"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Training data:\n"
]
},
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>result_Y</th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>All</th>\n",
" </tr>\n",
" <tr>\n",
" <th>decision_T</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4683</td>\n",
" <td>8297</td>\n",
" <td>12980</td>\n",
" <td>7786</td>\n",
" <td>4234</td>\n",
" <td>12020</td>\n",
" <td>12469</td>\n",
" <td>12531</td>\n",
" <td>25000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"result_Y 0 1 All\n",
"decision_T \n",
"0 4683 8297 12980\n",
"1 7786 4234 12020\n",
"All 12469 12531 25000"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"Test data:\n"
]
},
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
{
"data": {
"text/html": [
"<div>\n",
"<style scoped>\n",
" .dataframe tbody tr th:only-of-type {\n",
" vertical-align: middle;\n",
" }\n",
"\n",
" .dataframe tbody tr th {\n",
" vertical-align: top;\n",
" }\n",
"\n",
" .dataframe thead th {\n",
" text-align: right;\n",
" }\n",
"</style>\n",
"<table border=\"1\" class=\"dataframe\">\n",
" <thead>\n",
" <tr style=\"text-align: right;\">\n",
" <th>result_Y</th>\n",
" <th>0</th>\n",
" <th>1</th>\n",
" <th>All</th>\n",
" </tr>\n",
" <tr>\n",
" <th>decision_T</th>\n",
" <th></th>\n",
" <th></th>\n",
" <th></th>\n",
" </tr>\n",
" </thead>\n",
" <tbody>\n",
" <tr>\n",
" <th>0</th>\n",
" <td>4738</td>\n",
" <td>8249</td>\n",
" <td>12987</td>\n",
" <td>7803</td>\n",
" <td>4210</td>\n",
" <td>12013</td>\n",
" <td>12541</td>\n",
" <td>12459</td>\n",
" <td>25000</td>\n",
" </tr>\n",
" </tbody>\n",
"</table>\n",
"</div>"
],
"text/plain": [
"result_Y 0 1 All\n",
"decision_T \n",
"0 4738 8249 12987\n",
"1 7803 4210 12013\n",
"All 12541 12459 25000"
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# Set seed for reproducibility\n",
"#npr.seed(0)\n",
"\n",
"def generateDataNoUnobservables(nJudges_M=100, nSubjects_N=500, beta_X=1.0):\n",
"\n",
" df = pd.DataFrame()\n",
"\n",
" # Assign judge IDs as running numbering from 0 to nJudges_M - 1\n",
" df = df.assign(judgeID_J=np.repeat(range(0, nJudges_M), nSubjects_N))\n",
"\n",
" # Sample acceptance rates uniformly from a closed interval\n",
" # from 0.1 to 0.9 and round to tenth decimal place.\n",
" acceptance_rates = np.round(npr.uniform(.1, .9, nJudges_M), 10)\n",
"\n",
" # Replicate the rates so they can be attached to the corresponding judge ID.\n",
" df = df.assign(acceptanceRate_R=np.repeat(acceptance_rates, nSubjects_N))\n",
"\n",
" # Sample feature X from standard Gaussian distribution, N(0, 1).\n",
" df = df.assign(X=npr.normal(size=nJudges_M * nSubjects_N))\n",
"\n",
" # Calculate P(Y=0|X=x) = 1 / (1 + exp(-beta_X * x)) = sigmoid(beta_X * x)\n",
" df = df.assign(probabilities_Y=sigmoid(beta_X * df.X))\n",
"\n",
" df = df.assign(\n",
" result_Y=1-npr.binomial(n=1, p=df.probabilities_Y, size=nJudges_M * nSubjects_N))\n",
" # Invert the probabilities. ELABORATE COMMENT!\n",
" df.probabilities_Y = 1 - df.probabilities_Y\n",
"\n",
" # Sort by judges then probabilities in decreasing order\n",
" # I.e. the most dangerous for each judge are first.\n",
" df = df.sort_values(by=[\"judgeID_J\", \"probabilities_Y\"], ascending=False)\n",
"\n",
" # Iterate over the data. Subject is in the top (1-r)*100% if\n",
" # his within-judge-index is over acceptance threshold times\n",
" # the number of subjects assigned to each judge. If subject\n",
" # is over the limit they are assigned a zero, else one.\n",
" df.reset_index(drop=True, inplace=True)\n",
"\n",
" df['decision_T'] = np.where((df.index.values % nSubjects_N) <\n",
" ((1 - df['acceptanceRate_R']) * nSubjects_N),\n",
" 0, 1)\n",
"\n",
" # Halve the data set to test and train\n",
" train, test = train_test_split(df, test_size=0.5)\n",
" train_labeled = train.copy()\n",
" test_labeled = test.copy()\n",
" # Set results as NA if decision is negative.\n",
" train_labeled.loc[train_labeled.decision_T == 0, 'result_Y'] = np.nan\n",
" test_labeled.loc[test_labeled.decision_T == 0, 'result_Y'] = np.nan\n",
" return train_labeled, train, test_labeled, test, df\n",
"s_train_labeled, s_train, s_test_labeled, s_test, s_df = generateDataNoUnobservables()\n",
"display(pd.crosstab(s_df.decision_T, s_df.result_Y, margins=True))\n",
"print(\"Training data:\")\n",
"display(pd.crosstab(s_train.decision_T, s_train.result_Y, margins=True))\n",
"print(\"Test data:\")\n",
"display(pd.crosstab(s_test.decision_T, s_test.result_Y, margins=True))"
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Algorithms\n",
"\n",
"### Contraction algorithm\n",
"\n",
"Below is an implementation of Lakkaraju's team's algorithm presented in [their paper](https://helka.finna.fi/PrimoRecord/pci.acm3098066). Relevant parameters to be passed to the function are presented in the description."
]
},
{
"cell_type": "code",
"def contraction(df, judgeIDJ_col, decisionT_col, resultY_col, modelProbS_col,\n",
" accRateR_col, r):\n",
" '''\n",
" This is an implementation of the algorithm presented by Lakkaraju\n",
" et al. in their paper \"The Selective Labels Problem: Evaluating \n",
" Algorithmic Predictions in the Presence of Unobservables\" (2017).\n",
" \n",
" Parameters:\n",
" df = The (Pandas) data frame containing the data, judge decisions,\n",
" judge IDs, results and probability scores.\n",
" judgeIDJ_col = String, the name of the column containing the judges' IDs\n",
" in df.\n",
" decisionT_col = String, the name of the column containing the judges' decisions\n",
" resultY_col = String, the name of the column containing the realization\n",
" modelProbS_col = String, the name of the column containing the probability\n",
" scores from the black-box model B.\n",
" accRateR_col = String, the name of the column containing the judges' \n",
" acceptance rates\n",
" r = Float between 0 and 1, the given acceptance rate.\n",
" \n",
" Returns the estimated failure rate at acceptance rate r.\n",
" most_lenient_ID_q = df[judgeIDJ_col].loc[df[accRateR_col].idxmax()]\n",
" # Subset. \"D_q is the set of all observations judged by q.\"\n",
" D_q = df[df[judgeIDJ_col] == most_lenient_ID_q].copy()\n",
" # All observations of R_q have observed outcome labels.\n",
" # \"R_q is the set of observations in D_q with observed outcome labels.\"\n",
" R_q = D_q[D_q[decisionT_col] == 1].copy()\n",
" # Sort observations in R_q in descending order of confidence scores S and\n",
" # assign to R_sort_q.\n",
" # \"Observations deemed as high risk by B are at the top of this list\"\n",
" R_sort_q = R_q.sort_values(by=modelProbS_col, ascending=False)\n",
"\n",
" number_to_remove = int(\n",
" round((1.0 - r) * D_q.shape[0] - (D_q.shape[0] - R_q.shape[0])))\n",
"\n",
" # \"R_B is the list of observations assigned to t = 1 by B\"\n",
" R_B = R_sort_q[number_to_remove:R_sort_q.shape[0]]\n",
"\n",
" return np.sum(R_B[resultY_col] == 0) / D_q.shape[0]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\n",
"Generalized performance:\n",
"\n",
"$$\n",
"\\mathbf{gp} = \\sum_x f(x)\\delta(F(x) < r)P(X=x)\n",
"$$\n",
"\n",
"and empirical performance:\n",
"\n",
"$$\n",
"\\mathbf{ep} = \\dfrac{1}{n} \\sum_{(x, y) \\in \\mathcal{D}} \\delta(y=0) \\delta(F(x) < r)\n",
"$$\n",
"\n",
"where\n",
"\n",
"$$\n",
"$$\n",
"\n",
"and\n",
"\n",
"$$\n",
"F(x_0) = \\int P(x)~\\delta(P(Y=0|T=1, X=x) > P(Y=0|T=1, X=x_0)) ~ dx = \\int P(x)~\\delta(f(x) > f(x_0)) ~ dx.\n",
"$$\n"
"def getProbabilityForClass(x, model, class_value):\n",
" Function (wrapper) for obtaining the probability of a class given x and a \n",
" predictive model.\n",
" \n",
" x = individual features, an array, shape (observations, features)\n",
" model = a trained sklearn model. Predicts probabilities for given x. Should\n",
" accept input of size (observations, features)\n",
" class_value = the resulting class to predict (usually 0 or 1).\n",
" The probabilities of given class label for each x.\n",
" '''\n",
" if x.ndim == 1:\n",
" # if x is vector, transform to column matrix.\n",
" f_values = model.predict_proba(np.array(x).reshape(-1, 1))\n",
" else:\n",
" f_values = model.predict_proba(x)\n",
"\n",
" # Get correct column of predicted class, remove extra dimensions and return.\n",
" return f_values[:, model.classes_ == class_value].flatten()\n",
"\n",
"def cdf(x_0, model, class_value):\n",
" '''\n",
" Cumulative distribution function as described above.\n",
" \n",
" '''\n",
" prediction = lambda x: getProbabilityForClass(\n",
" np.array([x]).reshape(-1, 1), model, class_value)\n",
"\n",
"\n",
" x_values = np.linspace(-10, 10, 40000)\n",
"\n",
" x_preds = prediction(x_values)\n",
"\n",
" y_values = scs.norm.pdf(x_values)\n",
"\n",
" y_copy[prediction(x_values) > prediction_x_0[i]] = 0\n",
" \n",
" results[i] = si.simps(y_copy, x=x_values)\n",
"\n",
"#%timeit cdf(np.ones(1), logreg, 0)\n",
"#%timeit cdf(np.ones(10), logreg, 0)\n",
"#%timeit cdf(np.ones(100), logreg, 0)\n",
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"## Performance comparison\n",
"\n",
"Below we try to replicate the results obtained by Lakkaraju and compare their model's performance to the one of ours."
"def fitLogisticRegressionModel(x_train, y_train, x_test, class_value):\n",
" '''\n",
" Fit logistic regression model with given inputs. Checks their shape if \n",
" incompatible.\n",
" \n",
" Parameters:\n",
" \n",
" \n",
" Returns:\n",
" (1) Trained LogisticRegression model\n",
" (2) Probabilities for given test inputs for given class.\n",
" '''\n",
" # Instantiate the model (using the default parameters)\n",
" logreg = LogisticRegression(solver='lbfgs')\n",
"\n",
" # Check shape and fit the model.\n",
" if x_train.ndim == 1:\n",
" logreg = logreg.fit(x_train.values.reshape(-1, 1), y_train)\n",
" else:\n",
" logreg = logreg.fit(x_train, y_train)\n",
" # Check shape and predict probabilities.\n",
" if x_test.ndim == 1:\n",
" label_probs_logreg = logreg.predict_proba(x_test.values.reshape(-1, 1))\n",
" else:\n",
" label_probs_logreg = logreg.predict_proba(x_test)\n",
" return logreg, label_probs_logreg[:, logreg.classes_ == class_value]"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"### With unobservables in the data\n",
"Lakkaraju says that they used logistic regression. We train the predictive models using only *observed observations*, i.e. observations for which labels are available. We then predict the probability of negative outcome for all observations in the test data and attach it to our data set."
{
"name": "stdout",
"output_type": "stream",
"text": [
"1| 0 1 2 3 4 2| 0 1 2 3 4 3| 0 1 2 3 4 4| 0 1 2 3 4 5| 0 1 2 3 4 6| 0 1 2 3 4 7| 0 1 2 3 4 8| 0 1 2 3 4 "
"image/png": "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\n",
"text/plain": [
"<Figure size 1008x576 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"failure_rates = np.zeros((8, 5))\n",
"failure_sems = np.zeros((8, 5))\n",
"for r in np.arange(1, 9):\n",
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
" print(r, end=\"| \")\n",
" \n",
" f_rate_true = np.zeros(nIter)\n",
" f_rate_label = np.zeros(nIter)\n",
" f_rate_human = np.zeros(nIter)\n",
" f_rate_cont = np.zeros(nIter)\n",
" f_rate_caus = np.zeros(nIter)\n",
" \n",
" for i in range(nIter):\n",
" \n",
" print(i, end=\" \")\n",
" \n",
" train_labeled, train, test_labeled, test, df = generateData()\n",
"\n",
" logreg, predictions = fitLogisticRegressionModel(\n",
" train_labeled.dropna().X,\n",
" train_labeled.dropna().result_Y,\n",
" test.X, 0)\n",
" test = test.assign(B_prob_0_logreg = predictions)\n",
"\n",
" logreg, predictions_labeled = fitLogisticRegressionModel(\n",
" train_labeled.dropna().X,\n",
" train_labeled.dropna().result_Y,\n",
" test_labeled.X, 0)\n",
" test_labeled = test_labeled.assign(B_prob_0_logreg = predictions_labeled)\n",
"\n",
" #### True evaluation\n",
" # Sort by failure probabilities, subjects with the smallest risk are first.\n",
" test.sort_values(by='B_prob_0_logreg', inplace=True, ascending=True)\n",
"\n",
" to_release = int(round(test.shape[0] * r / 10))\n",
"\n",
" # Calculate failure rate as the ratio of failures to those who were given a\n",
" # positive decision, i.e. those whose probability of negative outcome was\n",
" # low enough.\n",
" f_rate_true[i] = np.sum(\n",
" test.result_Y[0:to_release] == 0) / test.shape[0]\n",
"\n",
" #### Labeled outcomes only\n",
" # Sort by failure probabilities, subjects with the smallest risk are first.\n",
" test_labeled.sort_values(by='B_prob_0_logreg',\n",
" inplace=True,\n",
" ascending=True)\n",
"\n",
" to_release = int(round(test_labeled.shape[0] * r / 10))\n",
"\n",
" f_rate_label[i] = np.sum(\n",
" test_labeled.result_Y[0:to_release] == 0) / test_labeled.shape[0]\n",
"\n",
" #### Human evaluation\n",
" # Get judges with correct leniency as list\n",
" correct_leniency_list = test_labeled.judgeID_J[\n",
" test_labeled['acceptanceRate_R'].round(1) == r / 10].values\n",
"\n",
" # Released are the people they judged and released, T = 1\n",
" released = test_labeled[test_labeled.judgeID_J.isin(correct_leniency_list)\n",
" & (test_labeled.decision_T == 1)]\n",
"\n",
" # Get their failure rate, aka ratio of reoffenders to number of people judged in total\n",
" f_rate_human[i] = np.sum(\n",
" released.result_Y == 0) / correct_leniency_list.shape[0]\n",
"\n",
" #### Contraction, logistic regression\n",
" f_rate_cont[i] = contraction(test_labeled, 'judgeID_J',\n",
" 'decision_T', 'result_Y',\n",
" 'B_prob_0_logreg',\n",
" 'acceptanceRate_R', r / 10)\n",
"\n",
" #### Causal model - empirical performance\n",
" #\n",
" f_rate_caus[i] = np.sum((test_labeled.dropna().result_Y == 0) & (\n",
" cdf(test_labeled.dropna().X, logreg, 0) < r /\n",
" 10)) / test_labeled.dropna().result_Y.shape[0]\n",
" \n",
" failure_rates[r - 1, 0] = np.mean(f_rate_true)\n",
" failure_rates[r - 1, 1] = np.mean(f_rate_label)\n",
" failure_rates[r - 1, 2] = np.mean(f_rate_human)\n",
" failure_rates[r - 1, 3] = np.mean(f_rate_cont)\n",
" failure_rates[r - 1, 4] = np.mean(f_rate_caus)\n",
" \n",
" failure_sems[r - 1, 0] = scs.sem(f_rate_true)\n",
" failure_sems[r - 1, 1] = scs.sem(f_rate_label)\n",
" failure_sems[r - 1, 2] = scs.sem(f_rate_human)\n",
" failure_sems[r - 1, 3] = scs.sem(f_rate_cont)\n",
" failure_sems[r - 1, 4] = scs.sem(f_rate_caus)\n",
"x_ax = np.arange(0.1, 0.9, 0.1)\n",
"plt.errorbar(x_ax, failure_rates[:, 0], label='True Evaluation', c='green', yerr=failure_sems[:, 0])\n",
"plt.errorbar(x_ax, failure_rates[:, 1], label='Labeled outcomes', c='magenta', yerr=failure_sems[:, 1])\n",
"plt.errorbar(x_ax, failure_rates[:, 2], label='Human evaluation', c='red', yerr=failure_sems[:, 2])\n",
"plt.errorbar(x_ax, failure_rates[:, 3], label='Contraction, log.', c='blue', yerr=failure_sems[:, 3])\n",
"plt.errorbar(x_ax, failure_rates[:, 4], label='Causal model, ep', c='black', yerr=failure_sems[:, 4])\n",
"\n",
"plt.title('Failure rate vs. Acceptance rate')\n",
"plt.xlabel('Acceptance rate')\n",
"plt.ylabel('Failure rate')\n",
"plt.legend()\n",
"plt.grid()\n",
"plt.show()"
]
},
{
"### Without unobservables"
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"1| 0 2| 0 3| 0 4| 0 5| 0 6| 0 7| 0 8| 0 "
"image/png": "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\n",
"<Figure size 1008x576 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
}
],
"source": [
"f_rates = np.zeros((8, 5))\n",
"f_sems = np.zeros((8, 5))\n",
"\n",
"nIter = 20\n",
"\n",
"for r in np.arange(1, 9):\n",
"\n",
" print(r, end=\"| \")\n",
"\n",
" s_f_rate_true = np.zeros(nIter)\n",
" s_f_rate_human = np.zeros(nIter)\n",
" s_f_rate_cont = np.zeros(nIter)\n",
" s_f_rate_caus = np.zeros(nIter)\n",
"\n",
" for i in range(nIter):\n",
"\n",
" print(i, end=\" \")\n",