Cleaned charts/data handling; fixed outdated norm.rvs() parameterization

Author: wrichert

ch11/Makefile

@@ -12,8 +12,7 @@
 import scipy
 from scipy.stats import norm, pearsonr
 
-DATA_DIR = os.path.join("..", "data")
-CHART_DIR = os.path.join("..", "charts")
+from utils import CHART_DIR
 
 
 def _plot_correlation_func(x, y):
@@ -39,19 +38,19 @@ def plot_correlation_demo():
     x = np.arange(0, 10, 0.2)
 
     pylab.subplot(221)
-    y = 0.5 * x + norm.rvs(1, loc=0, scale=.01, size=len(x))
+    y = 0.5 * x + norm.rvs(1, scale=.01, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.subplot(222)
-    y = 0.5 * x + norm.rvs(1, loc=0, scale=.1, size=len(x))
+    y = 0.5 * x + norm.rvs(1, scale=.1, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.subplot(223)
-    y = 0.5 * x + norm.rvs(1, loc=0, scale=1, size=len(x))
+    y = 0.5 * x + norm.rvs(1, scale=1, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.subplot(224)
-    y = norm.rvs(1, loc=0, scale=10, size=len(x))
+    y = norm.rvs(1, scale=10, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.autoscale(tight=True)
@@ -66,19 +65,19 @@ def plot_correlation_demo():
     x = np.arange(-5, 5, 0.2)
 
     pylab.subplot(221)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=.01, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=.01, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.subplot(222)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=.1, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=.1, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.subplot(223)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=1, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=1, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.subplot(224)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=10, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=10, size=len(x))
     _plot_correlation_func(x, y)
 
     pylab.autoscale(tight=True)

ch11/demo_corr.py

@@ -14,8 +14,7 @@
 from sklearn import linear_model, manifold, decomposition, datasets
 logistic = linear_model.LogisticRegression()
 
-
-CHART_DIR = os.path.join("..", "charts")
+from utils import CHART_DIR
 
 np.random.seed(3)
 

ch11/demo_mds.py

@@ -11,8 +11,7 @@
 import numpy as np
 from scipy.stats import norm, entropy
 
-DATA_DIR = os.path.join("..", "data")
-CHART_DIR = os.path.join("..", "charts")
+from utils import CHART_DIR
 
 
 def mutual_info(x, y, bins=10):
@@ -73,19 +72,19 @@ def plot_mi_demo():
     x = np.arange(0, 10, 0.2)
 
     pylab.subplot(221)
-    y = 0.5 * x + norm.rvs(1, loc=0, scale=.01, size=len(x))
+    y = 0.5 * x + norm.rvs(1, scale=.01, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.subplot(222)
-    y = 0.5 * x + norm.rvs(1, loc=0, scale=.1, size=len(x))
+    y = 0.5 * x + norm.rvs(1, scale=.1, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.subplot(223)
-    y = 0.5 * x + norm.rvs(1, loc=0, scale=1, size=len(x))
+    y = 0.5 * x + norm.rvs(1, scale=1, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.subplot(224)
-    y = norm.rvs(1, loc=0, scale=10, size=len(x))
+    y = norm.rvs(1, scale=10, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.autoscale(tight=True)
@@ -100,19 +99,19 @@ def plot_mi_demo():
     x = np.arange(-5, 5, 0.2)
 
     pylab.subplot(221)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=.01, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=.01, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.subplot(222)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=.1, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=.1, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.subplot(223)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=1, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=1, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.subplot(224)
-    y = 0.5 * x ** 2 + norm.rvs(1, loc=0, scale=10, size=len(x))
+    y = 0.5 * x ** 2 + norm.rvs(1, scale=10, size=len(x))
     _plot_mi_func(x, y)
 
     pylab.autoscale(tight=True)

ch11/demo_mi.py

@@ -16,12 +16,12 @@
 logistic = linear_model.LogisticRegression()
 
 
-CHART_DIR = os.path.join("..", "charts")
+from utils import CHART_DIR
 
 np.random.seed(3)
 
 x1 = np.arange(0, 10, .2)
-x2 = x1 + np.random.normal(loc=0, scale=1, size=len(x1))
+x2 = x1 + np.random.normal(scale=1, size=len(x1))
 
 
 def plot_simple_demo_1():
@@ -35,7 +35,7 @@ def plot_simple_demo_1():
     pylab.ylabel("$X_2$")
 
     x1 = np.arange(0, 10, .2)
-    x2 = x1 + np.random.normal(loc=0, scale=1, size=len(x1))
+    x2 = x1 + np.random.normal(scale=1, size=len(x1))
 
     good = (x1 > 5) | (x2 > 5)
     bad = ~good
@@ -89,7 +89,7 @@ def plot_simple_demo_2():
     pylab.ylabel("$X_2$")
 
     x1 = np.arange(0, 10, .2)
-    x2 = x1 + np.random.normal(loc=0, scale=1, size=len(x1))
+    x2 = x1 + np.random.normal(scale=1, size=len(x1))
 
     good = x1 > x2
     bad = ~good

ch11/demo_pca.py

@@ -0,0 +1,19 @@
+# This code is supporting material for the book
+# Building Machine Learning Systems with Python
+# by Willi Richert and Luis Pedro Coelho
+# published by PACKT Publishing
+#
+# It is made available under the MIT License
+
+import os
+
+DATA_DIR = os.path.join(
+    os.path.dirname(os.path.realpath(__file__)), "data")
+
+CHART_DIR = os.path.join(
+    os.path.dirname(os.path.realpath(__file__)), "charts")
+
+for d in [DATA_DIR, CHART_DIR]:
+    if not os.path.exists(d):
+        os.mkdir(d)
+