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=\"#Data-sets\" data-toc-modified-id=\"Data-sets-1\"><span class=\"toc-item-num\">1 </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-1.1\"><span class=\"toc-item-num\">1.1 </span>Synthetic data with unobservables</a></span></li><li><span><a href=\"#Data-without-unobservables\" data-toc-modified-id=\"Data-without-unobservables-1.2\"><span class=\"toc-item-num\">1.2 </span>Data without unobservables</a></span></li></ul></li><li><span><a href=\"#Algorithms\" data-toc-modified-id=\"Algorithms-2\"><span class=\"toc-item-num\">2 </span>Algorithms</a></span><ul class=\"toc-item\"><li><span><a href=\"#Contraction-algorithm\" data-toc-modified-id=\"Contraction-algorithm-2.1\"><span class=\"toc-item-num\">2.1 </span>Contraction algorithm</a></span></li><li><span><a href=\"#Causal-approach---metrics\" data-toc-modified-id=\"Causal-approach---metrics-2.2\"><span class=\"toc-item-num\">2.2 </span>Causal approach - metrics</a></span></li></ul></li><li><span><a href=\"#Performance-comparison\" data-toc-modified-id=\"Performance-comparison-3\"><span class=\"toc-item-num\">3 </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-3.1\"><span class=\"toc-item-num\">3.1 </span>With unobservables in the data</a></span></li><li><span><a href=\"#Without-unobservables\" data-toc-modified-id=\"Without-unobservables-3.2\"><span class=\"toc-item-num\">3.2 </span>Without unobservables</a></span></li></ul></li></ul></div>"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
"\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.) -->\n",
"\n",
"Imports and settings."
"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."
" '''Return value of sigmoid function (inverse of logit) at x.'''\n",
"\n",
"def dataWithUnobservables(nJudges_M=100,\n",
" nSubjects_N=500,\n",
" beta_X=1.0,\n",
" beta_Z=1.0,\n",
" beta_W=0.2,\n",
" add_noise_T=True):\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 the variables from standard Gaussian distributions.\n",
" df = df.assign(X=npr.normal(size=nJudges_M * nSubjects_N))\n",
" df = df.assign(Z=npr.normal(size=nJudges_M * nSubjects_N))\n",
" df = df.assign(W=npr.normal(size=nJudges_M * nSubjects_N))\n",
" probabilities_Y = sigmoid(beta_X * df.X + beta_Z * df.Z + beta_W * df.W)\n",
" df = df.assign(probabilities_Y=probabilities_Y)\n",
"\n",
" # Result is 0 if P(Y = 0| X = x; Z = z; W = w) >= 0.5 , 1 otherwise\n",
" df = df.assign(result_Y=np.where(probabilities_Y >= 0.5, 0, 1))\n",
" # For the conditional probabilities of T we add noise ~ N(0, 0.1)\n",
" probabilities_T = sigmoid(beta_X * df.X + beta_Z * df.Z)\n",
"\n",
" if add_noise_T:\n",
" probabilities_T += np.sqrt(0.1) * npr.normal(size=nJudges_M *\n",
" nSubjects_N)\n",
" df = df.assign(probabilities_T=probabilities_T)\n",
" # Sort by judges then probabilities in decreasing order\n",
" # Most dangerous for each judge are at the top.\n",
" df.sort_values(by=[\"judgeID_J\", \"probabilities_T\"],\n",
" ascending=False,\n",
" inplace=True)\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['decision_T'] = np.where((df.index.values % nSubjects_N) <\n",
" ((1 - df['acceptanceRate_R']) * nSubjects_N),\n",
" 0, 1)\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"
{
"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",
"\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 $p_y = P(Y=0)$\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 $Y \\sim \\text{Bernoulli}(\\frac{1}{1+exp\\{-\\beta_X \\cdot X\\}})$"
"def dataWithoutUnobservables(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=1|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",
" # Draw Y ~ Bernoulli(sigmoid(beta_X * x)) = Bin(1, p)\n",
" results = npr.binomial(n=1,\n",
" p=df.probabilities_Y,\n",
" size=nJudges_M * nSubjects_N)\n",
"\n",
" df = df.assign(result_Y=results)\n",
" # Invert the probabilities. P(Y=0 | X) = 1 - P(Y=1 | X)\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.sort_values(by=[\"judgeID_J\", \"probabilities_Y\"],\n",
" ascending=False,\n",
" inplace=True)\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"
{
"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",
"$$\n",
"\\mathbf{gp} = \\sum_{x\\in\\mathcal{X}} f(x)\\delta(F(x) < r)P(X=x)\n",
"$$\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",
"NB: in code the direction of inequality was changed. CDF changed to `bailIndicator` function.\n",
"\n",
"**Rationale for `bailIndicator`**\n",
"\n",
"* Bail decision is based on prediction $P(Y=0|T=1, X=x)$.\n",
" * Uniform over all judges\n",
"* Judges rationing: \"If this defendant is in the top 10% of \"dangerousness rank\" and my $r = 0.85$, I will jail him.\"\n",
"* Overall: this kind of defendant $(X=x)$ is usually in the $z^{th}$ percentile in dangerousness (sd +- $u$ percentiles). Now, what is the probability that this defendant has $z \\leq 1-r$?"
"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",
"# prediction = lambda x: getProbabilityForClass(\n",
"# np.array([x]).reshape(-1, 1), model, class_value)\n",
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
"# results = np.zeros(x_0.shape[0])\n",
"\n",
"# for i in range(x_0.shape[0]):\n",
"\n",
"# y_copy = y_values.copy()\n",
"\n",
"# y_copy[x_preds > prediction_x_0[i]] = 0\n",
"\n",
"# results[i] = si.simps(y_copy, x=x_values)\n",
"\n",
"# return results\n",
"\n",
"\n",
"def bailIndicator(r, y_model, x_train, x_test):\n",
" '''\n",
" Indicator function for whether a judge will bail or jail a suspect.\n",
" \n",
" Algorithm:\n",
" ----------\n",
" \n",
" (1) Calculate recidivism probabilities from training set with a trained \n",
" model and assign them to predictions_train.\n",
" \n",
" (2) Calculate recidivism probabilities from test set with the trained \n",
" model and assign them to predictions_test.\n",
" \n",
" (3) Construct a cumulative distribution function of the probabilities in\n",
" in predictions_train.\n",
" \n",
" (4)\n",
" For pred in predictions_test:\n",
" if pred belongs to a percentile (computed from step (3)) lower than r\n",
" return True\n",
" else\n",
" return False\n",
" \n",
" Returns:\n",
" --------\n",
" (1) Boolean list indicating a bail decision (bail = True).\n",
" '''\n",
" predictions_train = y_model.predict_proba(x_train)[:, 0]\n",
"\n",
" predictions_test = y_model.predict_proba(x_test)[:, 0]\n",
"\n",
" return [\n",
" scs.percentileofscore(predictions_train, pred, kind='weak') < r\n",
" for pred in predictions_test\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 fitLogisticRegression(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"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0.005576 0.002368 0.00975484 0.0024027 0.0050152 ]\n",
" [0.019912 0.0086 0.02109956 0.01658424 0.01691919]\n",
" [0.045936 0.01832 0.04945307 0.03069707 0.03660539]\n",
" [0.082064 0.033352 0.08653878 0.08995609 0.06328502]\n",
" [0.127528 0.047936 0.13063434 0.11355927 0.09697531]\n",
" [0.179456 0.065944 0.19077157 0.17911279 0.13350704]\n",
" [0.244872 0.089856 0.24493377 0.24659278 0.17521346]\n",
" [0.321696 0.113984 0.32884645 0.30272122 0.22299695]]\n"
}
],
"source": [
"failure_rates = np.zeros((8, 5))\n",
"failure_sems = np.zeros((8, 5))\n",
"for r in np.arange(1, 9):\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",
" for i in range(nIter):\n",
" # Create data\n",
" train_labeled, train, test_labeled, test, df = dataWithUnobservables()\n",
" # Fit model and calculate predictions\n",
" logreg, predictions = fitLogisticRegression(\n",
" train_labeled.dropna().X,\n",
" train_labeled.dropna().result_Y, test.X, 0)\n",
" test = test.assign(B_prob_0_logreg=predictions)\n",
" train_labeled.dropna().X,\n",
" train_labeled.dropna().result_Y, 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",
" # Released are the people they judged and released, T = 1\n",
" released = test_labeled[\n",
" 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', 'decision_T',\n",
" 'result_Y', 'B_prob_0_logreg',\n",
" 'acceptanceRate_R', r / 10)\n",
"\n",
" #### Causal model - empirical performance\n",
" #\n",
" released = bailIndicator(r * 10, logreg, train.X.values.reshape(-1, 1),\n",
" test_labeled.dropna().X.values.reshape(-1, 1))\n",
"\n",
" f_rate_caus[i] = np.sum(recidivated\n",
" & released) / test_labeled.dropna().shape[0]\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",
" 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,\n",
" failure_rates[:, 0],\n",
" label='True Evaluation',\n",
" c='green',\n",
" yerr=failure_sems[:, 0])\n",
"plt.errorbar(x_ax,\n",
" failure_rates[:, 1],\n",
" label='Labeled outcomes',\n",
" c='magenta',\n",
" yerr=failure_sems[:, 1])\n",
"plt.errorbar(x_ax,\n",
" failure_rates[:, 2],\n",
" label='Human evaluation',\n",
" c='red',\n",
" yerr=failure_sems[:, 2])\n",
"plt.errorbar(x_ax,\n",
" failure_rates[:, 3],\n",
" label='Contraction, log.',\n",
" c='blue',\n",
" yerr=failure_sems[:, 3])\n",
"plt.errorbar(x_ax,\n",
" failure_rates[:, 4],\n",
" label='Causal model, ep',\n",
" c='black',\n",
" yerr=failure_sems[:, 4])\n",
"plt.title('Failure rate vs. Acceptance rate with unobservables')\n",
"plt.xlabel('Acceptance rate')\n",
"plt.ylabel('Failure rate')\n",
"plt.legend()\n",
"plt.grid()\n",
"plt.show()\n",
"\n",
"print(failure_rates)"
"### Without unobservables"
"outputs": [
{
"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",
"<Figure size 1008x576 with 1 Axes>"
]
},
"metadata": {
"needs_background": "light"
},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"[[0.015 0.015 0.01962992 0.01439704 0.0297739 ]\n",
" [0.04148 0.04148 0.04322212 0.04912637 0.08153246]\n",
" [0.075696 0.075696 0.07457801 0.07281473 0.13389142]\n",
" [0.115016 0.115016 0.11908461 0.12088559 0.18920554]\n",
" [0.16228 0.16228 0.16279339 0.14916862 0.24129177]\n",
" [0.214056 0.214056 0.21129612 0.22366353 0.28695953]\n",
" [0.276344 0.276344 0.27453313 0.28847544 0.32376534]\n",
" [0.343248 0.343248 0.3449349 0.37472556 0.35145913]]\n"
"f_rates = np.zeros((8, 5))\n",
"f_sems = np.zeros((8, 5))\n",
"\n",
"\n",
"for r in np.arange(1, 9):\n",
"\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",
"\n",
" s_train_labeled, s_train, s_test_labeled, s_test, s_df = dataWithoutUnobservables(\n",
" s_train_labeled.dropna().X,\n",
" s_train_labeled.dropna().result_Y, s_test.X, 0)\n",
" s_test = s_test.assign(B_prob_0_logreg=predictions)\n",
"\n",
" s_train_labeled.dropna().X,\n",
" s_train_labeled.dropna().result_Y, s_test_labeled.X, 0)\n",
" B_prob_0_logreg=predictions_labeled)\n",
"\n",
" #### True evaluation\n",
" # Sort by estimated failure probabilities, subjects with the smallest risk are first.\n",
" s_sorted = s_test.sort_values(by='B_prob_0_logreg',\n",
" inplace=False,\n",
" ascending=True)\n",
"\n",
" to_release = int(round(s_sorted.shape[0] * r / 10))\n",
"\n",
" # Calculate failure rate as the ratio of failures to successes among those\n",
" # who were given a positive decision, i.e. those whose probability of negative\n",
" # outcome was low enough.\n",
" s_f_rate_true[i] = np.sum(\n",
" s_sorted.result_Y[0:to_release] == 0) / s_sorted.shape[0]\n",
"\n",
" #### \"Golden standard\"\n",
" # Sort by actual failure probabilities, subjects with the smallest risk are first.\n",
" s_sorted = s_test.sort_values(by='probabilities_Y',\n",
" inplace=False,\n",
" ascending=True)\n",
"\n",
" to_release = int(round(s_sorted.shape[0] * r / 10))\n",
"\n",
" # Calculate failure rate as the ratio of failures to successes among those\n",
" # who were given a positive decision, i.e. those whose probability of negative\n",
" # outcome was low enough.\n",
" s_f_rate_gs[i] = np.sum(\n",
" s_sorted.result_Y[0:to_release] == 0) / s_sorted.shape[0]\n",
"\n",
" #### Human error rate\n",
" # Get judges with correct leniency as list\n",
" correct_leniency_list = s_test_labeled.judgeID_J[\n",
" s_test_labeled['acceptanceRate_R'].round(1) == r / 10].values\n",
"\n",
" # Released are the people they judged and released, T = 1\n",
" released = s_test_labeled[\n",
" s_test_labeled.judgeID_J.isin(correct_leniency_list)\n",
" & (s_test_labeled.decision_T == 1)]\n",
"\n",
" # Get their failure rate, aka ratio of reoffenders to number of people judged in total\n",
" s_f_rate_human[i] = np.sum(\n",
" released.result_Y == 0) / correct_leniency_list.shape[0]\n",
"\n",
" #### Contraction\n",
" s_f_rate_cont[i] = contraction(s_test_labeled, 'judgeID_J',\n",
" 'decision_T', 'result_Y',\n",
" 'B_prob_0_logreg', 'acceptanceRate_R',\n",
" r / 10)\n",
" #### Causal model\n",
" recidivated = s_test_labeled.result_Y == 0\n",
"\n",
" released_for_bail = bailIndicator(\n",
" r * 10, s_logreg, s_train.X.values.reshape(-1, 1),\n",
" s_test_labeled.X.values.reshape(-1, 1))\n",
"\n",
" s_f_rate_caus[i] = np.sum(\n",
" recidivated & released_for_bail) / s_test_labeled.dropna().shape[0]\n",
"\n",
" f_rates[r - 1, 0] = np.mean(s_f_rate_true)\n",
" f_rates[r - 1, 1] = np.mean(s_f_rate_gs)\n",
" f_rates[r - 1, 2] = np.mean(s_f_rate_human)\n",
" f_rates[r - 1, 3] = np.mean(s_f_rate_cont)\n",
" f_rates[r - 1, 4] = np.mean(s_f_rate_caus)\n",
"\n",
" f_sems[r - 1, 2] = scs.sem(s_f_rate_human)\n",
" f_sems[r - 1, 3] = scs.sem(s_f_rate_cont)\n",
" f_sems[r - 1, 4] = scs.sem(s_f_rate_caus)\n",
"\n",
"x_ax = np.arange(0.1, 0.9, 0.1)\n",
"\n",
"plt.figure(figsize=(14, 8))\n",
"plt.errorbar(x_ax,\n",
" f_rates[:, 0],\n",
" label='True Evaluation',\n",
" c='green',\n",
" yerr=f_sems[:, 0])\n",
"plt.errorbar(x_ax,\n",
" f_rates[:, 1],\n",
" label='\"Golden standard\"',\n",
" f_rates[:, 2],\n",
" label='Human evaluation',\n",
" c='red',\n",
" yerr=f_sems[:, 2])\n",
"plt.errorbar(x_ax,\n",
" f_rates[:, 3],\n",
" label='Contraction, log.',\n",
" c='blue',\n",
" yerr=f_sems[:, 3])\n",
"plt.errorbar(x_ax,\n",
" f_rates[:, 4],\n",
" label='Causal model, ep',\n",
" yerr=f_sems[:, 4])\n",
"\n",
"plt.title('Failure rate vs. Acceptance rate without unobservables')\n",
"plt.xlabel('Acceptance rate')\n",
"plt.ylabel('Failure rate')\n",
"plt.legend()\n",
"plt.grid()\n",
"plt.show()\n",
"\n",
"print(f_rates)"
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
},
{
"cell_type": "code",
"execution_count": 148,
"metadata": {},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"(0.38130401665687785, 2.6503789913005405e-09)\n"
]
}
],
"source": [
"def f():\n",
" N_bootstraps = 100\n",
"\n",
" N_sample = int(s_train.X.values.shape[0]*0.05)\n",
"\n",
" res = np.zeros((N_bootstraps, 101))\n",
"\n",
" percs = np.arange(101)\n",
"\n",
" for i in range(N_bootstraps):\n",
"\n",
" sample = npr.choice(s_train.X.values, size=N_sample)\n",
"\n",
" predictions_sample = s_logreg.predict_proba(sample.reshape(-1, 1))[:, 0]\n",
"\n",
" #predictions_test = y_model.predict_proba(s_train.X.values.reshape(-1, 1))[:, 0]\n",
"\n",
" res[i, :] = np.percentile(predictions_sample, percs)\n",
"\n",
"#%timeit bailIndicator(50, logreg, train.X.values.reshape(-1, 1), test_labeled.dropna().X.values.reshape(-1, 1))\n",
"\n",
"print(si.quad(lambda x: logreg.predict_proba(np.array([x]).reshape(-1, 1))[:, 0] * bailIndicator(99, logreg, train.X.values.reshape(-1, 1), np.array([x]).reshape(-1, 1)) * scs.norm.pdf(x), -np.inf, np.inf))"
]
}
],
"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",
},
"toc": {
"base_numbering": 1,
"nav_menu": {},
"number_sections": true,
"sideBar": true,
"skip_h1_title": true,
"title_cell": "Table of Contents",
"title_sidebar": "Contents",
"toc_cell": true,
"toc_position": {
"height": "calc(100% - 180px)",
"left": "10px",
"top": "150px",
"width": "300.7px"