Merge branch 'chap2-style' into examples-style

Conflicts:
	Chapter2_MorePyMC/MorePyMC.ipynb

Author: eli-b

Chapter2_MorePyMC/MorePyMC.ipynb

@@ -300,6 +300,7 @@
       "import numpy as np\n",
       "n_data_points = 5  # in CH1 we had ~70 data points\n",
       "\n",
+      "\n",
       "@pm.deterministic\n",
       "def lambda_(tau=tau, lambda_1=lambda_1, lambda_2=lambda_2):\n",
       "    out = np.zeros(n_data_points)\n",
@@ -532,7 +533,7 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "alpha = 1./20.\n",
+      "alpha = 1. / 20.\n",
       "lambda_1, lambda_2 = pm.rexponential(alpha, 2)\n",
       "print lambda_1, lambda_2"
      ],
@@ -579,7 +580,7 @@
      "collapsed": false,
      "input": [
       "plt.bar(np.arange(80), data, color=\"#348ABD\")\n",
-      "plt.bar(tau-1, data[tau - 1], color=\"r\", label=\"user behaviour changed\")\n",
+      "plt.bar(tau - 1, data[tau - 1], color=\"r\", label=\"user behaviour changed\")\n",
       "plt.xlabel(\"Time (days)\")\n",
       "plt.ylabel(\"count of text-msgs received\")\n",
       "plt.title(\"Artificial dataset\")\n",
@@ -616,18 +617,18 @@
      "input": [
       "def plot_artificial_sms_dataset():\n",
       "    tau = pm.rdiscrete_uniform(0, 80)\n",
-      "    alpha = 1./20.\n",
+      "    alpha = 1. / 20.\n",
       "    lambda_1, lambda_2 = pm.rexponential(alpha, 2)\n",
       "    data = np.r_[pm.rpoisson(lambda_1, tau), pm.rpoisson(lambda_2, 80 - tau)]\n",
       "    plt.bar(np.arange(80), data, color=\"#348ABD\")\n",
-      "    plt.bar(tau - 1, data[tau-1], color=\"r\", label=\"user behaviour changed\")\n",
+      "    plt.bar(tau - 1, data[tau - 1], color=\"r\", label=\"user behaviour changed\")\n",
       "    plt.xlim(0, 80)\n",
       "\n",
       "figsize(12.5, 5)\n",
       "plt.title(\"More example of artificial datasets\")\n",
       "for i in range(4):\n",
       "    plt.subplot(4, 1, i)\n",
-      "    plot_artificial_sms_dataset()\n"
+      "    plot_artificial_sms_dataset()"
      ],
      "language": "python",
      "metadata": {},
@@ -709,7 +710,7 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "#set constants\n",
+      "# set constants\n",
       "p_true = 0.05  # remember, this is unknown.\n",
       "N = 1500\n",
       "\n",
@@ -775,10 +776,10 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "#include the observations, which are Bernoulli\n",
+      "# include the observations, which are Bernoulli\n",
       "obs = pm.Bernoulli(\"obs\", p, value=occurrences, observed=True)\n",
       "\n",
-      "#To be explained in chapter 3\n",
+      "# To be explained in chapter 3\n",
       "mcmc = pm.MCMC([p, obs])\n",
       "mcmc.sample(18000, 1000)"
      ],
@@ -860,15 +861,15 @@
       "import pymc as pm\n",
       "figsize(12, 4)\n",
       "\n",
-      "#these two quantities are unknown to us.\n",
+      "# these two quantities are unknown to us.\n",
       "true_p_A = 0.05\n",
       "true_p_B = 0.04\n",
       "\n",
-      "#notice the unequal sample sizes -- no problem in Bayesian analysis.\n",
+      "# notice the unequal sample sizes -- no problem in Bayesian analysis.\n",
       "N_A = 1500\n",
       "N_B = 750\n",
       "\n",
-      "#generate some observations\n",
+      "# generate some observations\n",
       "observations_A = pm.rbernoulli(true_p_A, N_A)\n",
       "observations_B = pm.rbernoulli(true_p_B, N_B)\n",
       "print \"Obs from Site A: \", observations_A[:30].astype(int), \"...\"\n",
@@ -978,7 +979,7 @@
      "input": [
       "figsize(12.5, 10)\n",
       "\n",
-      "#histogram of posteriors\n",
+      "# histogram of posteriors\n",
       "\n",
       "ax = plt.subplot(311)\n",
       "\n",
@@ -1257,7 +1258,7 @@
       "                        fc=first_coin_flips,\n",
       "                        sc=second_coin_flips):\n",
       "\n",
-      "    observed = fc*t_a + (1-fc)*sc\n",
+      "    observed = fc * t_a + (1 - fc) * sc\n",
       "    return observed.sum() / float(N)"
      ],
      "language": "python",
@@ -1360,7 +1361,7 @@
      "input": [
       "figsize(12.5, 3)\n",
       "p_trace = mcmc.trace(\"freq_cheating\")[:]\n",
-      "plt.hist(p_trace, histtype=\"stepfilled\", normed=True, alpha=0.85, bins=30, \n",
+      "plt.hist(p_trace, histtype=\"stepfilled\", normed=True, alpha=0.85, bins=30,\n",
       "         label=\"posterior distribution\", color=\"#348ABD\")\n",
       "plt.vlines([.05, .35], [0, 0], [5, 5], alpha=0.3)\n",
       "plt.xlim(0, 1)\n",
@@ -1415,9 +1416,10 @@
      "input": [
       "p = pm.Uniform(\"freq_cheating\", 0, 1)\n",
       "\n",
+      "\n",
       "@pm.deterministic\n",
       "def p_skewed(p=p):\n",
-      "    return 0.5*p + 0.25"
+      "    return 0.5 * p + 0.25"
      ],
      "language": "python",
      "metadata": {},
@@ -1491,7 +1493,7 @@
      "input": [
       "figsize(12.5, 3)\n",
       "p_trace = mcmc.trace(\"freq_cheating\")[:]\n",
-      "plt.hist(p_trace, histtype=\"stepfilled\", normed=True, alpha=0.85, bins=30, \n",
+      "plt.hist(p_trace, histtype=\"stepfilled\", normed=True, alpha=0.85, bins=30,\n",
       "         label=\"posterior distribution\", color=\"#348ABD\")\n",
       "plt.vlines([.05, .35], [0, 0], [5, 5], alpha=0.2)\n",
       "plt.xlim(0, 1)\n",
@@ -1539,7 +1541,7 @@
       "N = 10\n",
       "x = np.empty(N, dtype=object)\n",
       "for i in range(0, N):\n",
-      "    x[i] = pm.Exponential('x_%i' % i, (i+1)**2)"
+      "    x[i] = pm.Exponential('x_%i' % i, (i + 1) ** 2)"
      ],
      "language": "python",
      "metadata": {},
@@ -1575,10 +1577,10 @@
       "challenger_data = np.genfromtxt(\"data/challenger_data.csv\", skip_header=1,\n",
       "                                usecols=[1, 2], missing_values=\"NA\",\n",
       "                                delimiter=\",\")\n",
-      "#drop the NA values\n",
+      "# drop the NA values\n",
       "challenger_data = challenger_data[~np.isnan(challenger_data[:, 1])]\n",
       "\n",
-      "#plot it, as a function of tempature (the first column)\n",
+      "# plot it, as a function of tempature (the first column)\n",
       "print \"Temp (F), O-Ring failure?\"\n",
       "print challenger_data\n",
       "\n",
@@ -1587,7 +1589,7 @@
       "plt.yticks([0, 1])\n",
       "plt.ylabel(\"Damage Incident?\")\n",
       "plt.xlabel(\"Outside temperature (Fahrenheit)\")\n",
-      "plt.title(\"Defects of the Space Shuttle O-Rings vs temperature\")\n"
+      "plt.title(\"Defects of the Space Shuttle O-Rings vs temperature\")"
      ],
      "language": "python",
      "metadata": {},
@@ -1769,9 +1771,9 @@
       "parameters = zip(mu, tau, colors)\n",
       "\n",
       "for _mu, _tau, _color in parameters:\n",
-      "    plt.plot(x, nor.pdf(x, _mu, scale=1./_tau),\n",
+      "    plt.plot(x, nor.pdf(x, _mu, scale=1. / _tau),\n",
       "             label=\"$\\mu = %d,\\;\\\\tau = %.1f$\" % (_mu, _tau), color=_color)\n",
-      "    plt.fill_between(x, nor.pdf(x, _mu, scale=1./_tau), color=_color,\n",
+      "    plt.fill_between(x, nor.pdf(x, _mu, scale=1. / _tau), color=_color,\n",
       "                     alpha=.33)\n",
       "\n",
       "plt.legend(loc=\"upper right\")\n",
@@ -1820,14 +1822,14 @@
       "temperature = challenger_data[:, 0]\n",
       "D = challenger_data[:, 1]  # defect or not?\n",
       "\n",
-      "#notice the`value` here. We explain why below.\n",
+      "# notice the`value` here. We explain why below.\n",
       "beta = pm.Normal(\"beta\", 0, 0.001, value=0)\n",
       "alpha = pm.Normal(\"alpha\", 0, 0.001, value=0)\n",
       "\n",
       "\n",
       "@pm.deterministic\n",
       "def p(t=temperature, alpha=alpha, beta=beta):\n",
-      "    return 1.0 / (1. + np.exp(beta*t + alpha))\n"
+      "    return 1.0 / (1. + np.exp(beta * t + alpha))"
      ],
      "language": "python",
      "metadata": {},
@@ -1920,7 +1922,7 @@
       "\n",
       "figsize(12.5, 6)\n",
       "\n",
-      "#histogram of the samples:\n",
+      "# histogram of the samples:\n",
       "plt.subplot(211)\n",
       "plt.title(r\"Posterior distributions of the variables $\\alpha, \\beta$\")\n",
       "plt.hist(beta_samples, histtype='stepfilled', bins=35, alpha=0.85,\n",
@@ -1963,7 +1965,7 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "t = np.linspace(temperature.min() - 5, temperature.max()+5, 50)[:, None]\n",
+      "t = np.linspace(temperature.min() - 5, temperature.max() + 5, 50)[:, None]\n",
       "p_t = logistic(t.T, beta_samples, alpha_samples)\n",
       "\n",
       "mean_prob_t = p_t.mean(axis=0)"
@@ -2164,8 +2166,8 @@
       "plt.title(\"Simulated dataset using posterior parameters\")\n",
       "figsize(12.5, 6)\n",
       "for i in range(4):\n",
-      "    ax = plt.subplot(4, 1, i+1)\n",
-      "    plt.scatter(temperature, simulations[1000*i, :], color=\"k\",\n",
+      "    ax = plt.subplot(4, 1, i + 1)\n",
+      "    plt.scatter(temperature, simulations[1000 * i, :], color=\"k\",\n",
       "                s=50, alpha=0.6)"
      ],
      "language": "python",
@@ -2369,7 +2371,7 @@
       "plt.title(\"Random model\")\n",
       "\n",
       "# constant model\n",
-      "constant_prob = 7./23*np.ones(23)\n",
+      "constant_prob = 7. / 23 * np.ones(23)\n",
       "separation_plot(constant_prob, D)\n",
       "plt.title(\"Constant-prediction model\")"
      ],
@@ -2448,7 +2450,7 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "#type your code here.\n",
+      "# type your code here.\n",
       "figsize(12.5, 4)\n",
       "\n",
       "plt.scatter(alpha_samples, beta_samples, alpha=0.1)\n",