Merge pull request CamDavidsonPilon#199 from eli-b/examples-style

ExamplesFromChapters coding style

Author: CamDavidsonPilon

ExamplesFromChapters/Chapter1/SMS_behaviour.py

@@ -4,24 +4,25 @@
 count_data = np.loadtxt("../../Chapter1_Introduction/data/txtdata.csv")
 n_count_data = len(count_data)
 
-alpha = 1.0/count_data.mean() #recall count_data is 
-                              #the variable that holds our txt counts
-                              
-lambda_1 = pm.Exponential( "lambda_1",  alpha )
-lambda_2 = pm.Exponential( "lambda_2", alpha )
+alpha = 1.0 / count_data.mean()  # recall count_data is
+                                 # the variable that holds our txt counts
+
+lambda_1 = pm.Exponential("lambda_1",  alpha)
+lambda_2 = pm.Exponential("lambda_2", alpha)
+
+tau = pm.DiscreteUniform("tau", lower=0, upper=n_count_data)
 
-tau = pm.DiscreteUniform( "tau", lower = 0, upper = n_count_data )
 
 @pm.deterministic
-def lambda_( tau = tau, lambda_1 = lambda_1, lambda_2 = lambda_2 ):
-    out = np.zeros( n_count_data )  
-    out[:tau] = lambda_1 #lambda before tau is lambda1
-    out[tau:] = lambda_2 #lambda after tau is lambda2
+def lambda_(tau=tau, lambda_1=lambda_1, lambda_2=lambda_2):
+    out = np.zeros(n_count_data)
+    out[:tau] = lambda_1  # lambda before tau is lambda1
+    out[tau:] = lambda_2  # lambda after tau is lambda2
     return out
-    
-observation = pm.Poisson( "obs", lambda_, value = count_data, observed = True)
-model = pm.Model( [observation, lambda_1, lambda_2, tau] )
+
+observation = pm.Poisson("obs", lambda_, value=count_data, observed=True)
+model = pm.Model([observation, lambda_1, lambda_2, tau])
 
 
 mcmc = pm.MCMC(model)
-mcmc.sample( 100000, 50000, 1 )
+mcmc.sample(100000, 50000, 1)

ExamplesFromChapters/Chapter2/ABtesting.py

@@ -5,37 +5,35 @@
 
 import pymc as pm
 
-#these two quantities are unknown to us.
-true_p_A = 0.05 
+# these two quantities are unknown to us.
+true_p_A = 0.05
 true_p_B = 0.04
 
-#notice the unequal sample sizes -- no problem in Bayesian analysis.
+# notice the unequal sample sizes -- no problem in Bayesian analysis.
 N_A = 1500
-N_B = 1000 
+N_B = 1000
 
-#generate data
-observations_A = pm.rbernoulli( true_p_A, N_A )
-observations_B = pm.rbernoulli( true_p_B, N_B )
+# generate data
+observations_A = pm.rbernoulli(true_p_A, N_A)
+observations_B = pm.rbernoulli(true_p_B, N_B)
 
 
-
-#set up the pymc model. Again assume Uniform priors for p_A and p_B
-
+# set up the pymc model. Again assume Uniform priors for p_A and p_B
 p_A = pm.Uniform("p_A", 0, 1)
 p_B = pm.Uniform("p_B", 0, 1)
 
 
-#define the deterministic delta function. This is our unknown of interest.
+# define the deterministic delta function. This is our unknown of interest.
 
 @pm.deterministic
-def delta( p_A = p_A, p_B = p_B ):
+def delta(p_A=p_A, p_B=p_B):
     return p_A - p_B
 
 
-#set of observations, in this case we have two observation datasets. 
-obs_A = pm.Bernoulli( "obs_A", p_A, value = observations_A, observed = True )
-obs_B = pm.Bernoulli( "obs_B", p_B, value = observations_B, observed = True )
+# set of observations, in this case we have two observation datasets.
+obs_A = pm.Bernoulli("obs_A", p_A, value=observations_A, observed=True)
+obs_B = pm.Bernoulli("obs_B", p_B, value=observations_B, observed=True)
 
-#to be explained in chapter 3. 
-mcmc = pm.MCMC( [p_A, p_B, delta, obs_A, obs_B] )
-mcmc.sample( 20000, 1000)
+# to be explained in chapter 3.
+mcmc = pm.MCMC([p_A, p_B, delta, obs_A, obs_B])
+mcmc.sample(20000, 1000)

ExamplesFromChapters/Chapter2/FreqOfCheaters.py

@@ -1,15 +1,17 @@
 import pymc as pm
 
-p = pm.Uniform( "freq_cheating", 0, 1) 
+p = pm.Uniform("freq_cheating", 0, 1)
+
 
 @pm.deterministic
-def p_skewed( p =  p ):
-    return 0.5*p + 0.25
-    
-yes_responses = pm.Binomial( "number_cheaters", 100, p_skewed, value = 35, observed = True )
-                                
-model = pm.Model( [yes_responses, p_skewed, p ] )
-
-### To Be Explained in Chapter 3!
+def p_skewed(p=p):
+    return 0.5 * p + 0.25
+
+yes_responses = pm.Binomial(
+    "number_cheaters", 100, p_skewed, value=35, observed=True)
+
+model = pm.Model([yes_responses, p_skewed, p])
+
+# To Be Explained in Chapter 3!
 mcmc = pm.MCMC(model)
-mcmc.sample( 50000, 25000 )
+mcmc.sample(50000, 25000)

ExamplesFromChapters/Chapter2/ORingFailure.py

@@ -1,28 +1,32 @@
+import numpy as np
 import pymc as pm
 
 
-challenger_data = np.genfromtxt("../../Chapter2_MorePyMC/data/challenger_data.csv", skip_header = 1, usecols=[1,2], missing_values="NA", delimiter=",")
-#drop the NA values
-challenger_data = challenger_data[ ~np.isnan(challenger_data[:,1]) ]
+challenger_data = np.genfromtxt(
+    "../../Chapter2_MorePyMC/data/challenger_data.csv",
+    skip_header=1, usecols=[1, 2], missing_values="NA", delimiter=",")
+# drop the NA values
+challenger_data = challenger_data[~np.isnan(challenger_data[:, 1])]
 
 
-temperature = challenger_data[:,0]
-D = challenger_data[:,1] #defect or not?
+temperature = challenger_data[:, 0]
+D = challenger_data[:, 1]  # defect or not?
+
+beta = pm.Normal("beta", 0, 0.001, value=0)
+alpha = pm.Normal("alpha", 0, 0.001, value=0)
 
-beta = pm.Normal( "beta", 0, 0.001, value = 0 )
-alpha = pm.Normal( "alpha", 0, 0.001, value = 0 )
 
 @pm.deterministic
-def p( temp = temperature, alpha = alpha, beta = beta):
-    return 1.0/( 1. + np.exp( beta*temperature + alpha) ) 
+def p(temp=temperature, alpha=alpha, beta=beta):
+    return 1.0 / (1. + np.exp(beta * temperature + alpha))
 
 
-observed = pm.Bernoulli( "bernoulli_obs", p, value = D, observed=True)
+observed = pm.Bernoulli("bernoulli_obs", p, value=D, observed=True)
 
-model = pm.Model( [observed, beta, alpha] )
+model = pm.Model([observed, beta, alpha])
 
-#mysterious code to be explained in Chapter 3
+# mysterious code to be explained in Chapter 3
 map_ = pm.MAP(model)
 map_.fit()
-mcmc = pm.MCMC( model )
-mcmc.sample( 260000, 220000, 2 )
+mcmc = pm.MCMC(model)
+mcmc.sample(260000, 220000, 2)

ExamplesFromChapters/Chapter3/ClusteringWithGaussians.py

@@ -2,37 +2,40 @@
 import pymc as pm
 
 
-data = np.loadtxt( "../../Chapter3_MCMC/data/mixture_data.csv",  delimiter="," )
+data = np.loadtxt("../../Chapter3_MCMC/data/mixture_data.csv",  delimiter=",")
 
 
-p = pm.Uniform( "p", 0, 1)
+p = pm.Uniform("p", 0, 1)
 
-assignment = pm.Categorical("assignment", [p, 1-p], size = data.shape[0] ) 
+assignment = pm.Categorical("assignment", [p, 1 - p], size=data.shape[0])
 
-taus = 1.0/pm.Uniform( "stds", 0, 100, size= 2)**2 #notice the size!
-centers = pm.Normal( "centers", [150, 150], [0.001, 0.001], size =2 )
+taus = 1.0 / pm.Uniform("stds", 0, 100, size=2) ** 2  # notice the size!
+centers = pm.Normal("centers", [150, 150], [0.001, 0.001], size=2)
 
 """
 The below deterministic functions map a assingment, in this case 0 or 1,
 to a set of parameters, located in the (1,2) arrays `taus` and `centers.`
 """
 
-@pm.deterministic 
-def center_i( assignment = assignment, centers = centers ):
-        return centers[ assignment] 
 
 @pm.deterministic
-def tau_i( assignment = assignment, taus = taus ):
-        return taus[ assignment] 
+def center_i(assignment=assignment, centers=centers):
+        return centers[assignment]
 
-#and to combine it with the observations:
-observations = pm.Normal( "obs", center_i, tau_i, value = data, observed = True )
 
-#below we create a model class
-model = pm.Model( [p, assignment, taus, centers ] )
+@pm.deterministic
+def tau_i(assignment=assignment, taus=taus):
+        return taus[assignment]
+
+# and to combine it with the observations:
+observations = pm.Normal("obs", center_i, tau_i,
+                         value=data, observed=True)
+
+# below we create a model class
+model = pm.Model([p, assignment, taus, centers])
 
 
-map_ = pm.MAP( model )
+map_ = pm.MAP(model)
 map_.fit()
-mcmc = pm.MCMC( model )
-mcmc.sample( 100000, 50000 )
+mcmc = pm.MCMC(model)
+mcmc.sample(100000, 50000)

Prologue/Prologue.ipynb

@@ -187,6 +187,8 @@
      "collapsed": false,
      "input": [
       "from IPython.core.display import HTML\n",
+      "\n",
+      "\n",
       "def css_styling():\n",
       "    styles = open(\"../styles/custom.css\", \"r\").read()\n",
       "    return HTML(styles)\n",
@@ -280,4 +282,4 @@
    "metadata": {}
   }
  ]
-}
+}

sandbox/ABCtests.ipynb

@@ -29,14 +29,15 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "obs = np.array( [0,0,1] )\n",
+      "obs = np.array([0, 0, 1])\n",
       "\n",
       "uni = pm.Uniform(\"prop\", 0, 1)\n",
-      "fake_obs = pm.Bernoulli(\"fake_obs\", uni, size=3 )\n",
+      "fake_obs = pm.Bernoulli(\"fake_obs\", uni, size=3)\n",
+      "\n",
       "\n",
       "@pm.deterministic\n",
-      "def accept(uni = uni, fake_obs = fake_obs, obs = obs):\n",
-      "    if np.array_equal( fake_obs, obs ):\n",
+      "def accept(uni=uni, fake_obs=fake_obs, obs=obs):\n",
+      "    if np.array_equal(fake_obs, obs):\n",
       "        return uni\n",
       "    else:\n",
       "        return None"
@@ -50,7 +51,7 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "mcmc = pm.MCMC([uni, fake_obs, accept] )"
+      "mcmc = pm.MCMC([uni, fake_obs, accept])"
      ],
      "language": "python",
      "metadata": {},
@@ -99,7 +100,7 @@
      "cell_type": "code",
      "collapsed": false,
      "input": [
-      "hist( samples[samples > 0] )"
+      "hist(samples[samples > 0])"
      ],
      "language": "python",
      "metadata": {},