update parsing scripts (rasbt#43)

.travis.yml

@@ -22,10 +22,17 @@ addons:
 install:
     - sudo apt-get update
     - source .travis/install_travis_env.sh
+
+before_script: # configure a headless display to test plot generation
+  - "export DISPLAY=:99.0"
+  - "sh -e /etc/init.d/xvfb start"
+  - sleep 3 # give xvfb some time to start
+
 script:
     - bash .travis/run_travis_tests.sh
 #after_success:
 #    - if [[ "${COVERAGE}" == "true" ]]; then coveralls; codecov; else echo "failed"; fi
+
 notifications:
     email:
         recipients:

code/.convert_notebook_to_script.py

@@ -7,7 +7,6 @@
 import argparse
 import os
 import subprocess
-import textwrap
 
 
 def convert(input_path, output_path):
@@ -26,15 +25,23 @@ def cleanup(path):
 
     clean_content = []
     imports = []
+    existing_imports = set()
     with open(path, 'r') as f:
         next(f)
         next(f)
         for line in f:
+            line = line.rstrip(' ')
             if line.startswith(skip_lines_startwith):
                 continue
-            if line.startswith('import') or (
-                    'from' in line and 'import' in line):
-                imports.append(line)
+            if line.startswith('import ') or (
+                    'from ' in line and 'import ' in line):
+                if 'from __future__ import print_function' in line:
+                    if line != imports[0]:
+                        imports.insert(0, line)
+                else:
+                    if line.strip() not in existing_imports:
+                        imports.append(line)
+                        existing_imports.add(line.strip())
             else:
                 clean_content.append(line)
 

code/ch02/ch02.ipynb

@@ -1363,7 +1363,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 6,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {

code/ch02/ch02.py

@@ -4,7 +4,6 @@
 import numpy as np
 import pandas as pd
 import matplotlib.pyplot as plt
-import numpy as np
 from matplotlib.colors import ListedColormap
 
 # *Python Machine Learning 2nd Edition* by [Sebastian Raschka](https://sebastianraschka.com), Packt Publishing Ltd. 2017

code/ch03/ch03.ipynb

@@ -1743,7 +1743,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 4,
    "metadata": {},
    "outputs": [
     {
@@ -1758,6 +1758,15 @@
    "source": [
     "! python ../.convert_notebook_to_script.py --input ch03.ipynb --output ch03.py"
    ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {
+    "collapsed": true
+   },
+   "outputs": [],
+   "source": []
   }
  ],
  "metadata": {

code/ch03/ch03.py

@@ -11,16 +11,9 @@
 from sklearn.metrics import accuracy_score
 from matplotlib.colors import ListedColormap
 import matplotlib.pyplot as plt
-import matplotlib.pyplot as plt
-import numpy as np
 from sklearn.linear_model import LogisticRegression
 from sklearn.svm import SVC
 from sklearn.linear_model import SGDClassifier
-import matplotlib.pyplot as plt
-import numpy as np
-from sklearn.svm import SVC
-import matplotlib.pyplot as plt
-import numpy as np
 from sklearn.tree import DecisionTreeClassifier
 from pydotplus import graph_from_dot_data
 from sklearn.tree import export_graphviz

code/ch04/ch04.ipynb

@@ -2522,7 +2522,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 2,
    "metadata": {},
    "outputs": [
     {

code/ch04/ch04.py

@@ -5,25 +5,19 @@
 from io import StringIO
 import sys
 from sklearn.preprocessing import Imputer
-import pandas as pd
 import numpy as np
 from sklearn.preprocessing import LabelEncoder
 from sklearn.preprocessing import OneHotEncoder
 from sklearn.model_selection import train_test_split
 from sklearn.preprocessing import MinMaxScaler
 from sklearn.preprocessing import StandardScaler
 from sklearn.linear_model import LogisticRegression
-from sklearn.linear_model import LogisticRegression
 import matplotlib.pyplot as plt
 from sklearn.base import clone
 from itertools import combinations
-import numpy as np
 from sklearn.metrics import accuracy_score
-from sklearn.model_selection import train_test_split
-import matplotlib.pyplot as plt
 from sklearn.neighbors import KNeighborsClassifier
 from sklearn.ensemble import RandomForestClassifier
-importances = forest.feature_importances_
 from sklearn.feature_selection import SelectFromModel
 
 # *Python Machine Learning 2nd Edition* by [Sebastian Raschka](https://sebastianraschka.com), Packt Publishing Ltd. 2017
@@ -592,6 +586,7 @@ def _calc_score(self, X_train, y_train, X_test, y_test, indices):
                                 random_state=1)
 
 forest.fit(X_train, y_train)
+importances = forest.feature_importances_
 
 indices = np.argsort(importances)[::-1]
 

code/ch05/ch05.ipynb

@@ -2125,7 +2125,7 @@
      "output_type": "stream",
      "text": [
       "[NbConvertApp] Converting notebook ch05.ipynb to script\n",
-      "[NbConvertApp] Writing 27719 bytes to ch05.py\n"
+      "[NbConvertApp] Writing 27705 bytes to ch05.py\n"
      ]
     }
    ],

code/ch05/ch05.py

@@ -10,19 +10,11 @@
 from matplotlib.colors import ListedColormap
 from sklearn.linear_model import LogisticRegression
 from sklearn.discriminant_analysis import LinearDiscriminantAnalysis as LDA
-from sklearn.linear_model import LogisticRegression
 from scipy.spatial.distance import pdist, squareform
 from scipy import exp
 from scipy.linalg import eigh
-import numpy as np
-import matplotlib.pyplot as plt
 from sklearn.datasets import make_moons
-from sklearn.decomposition import PCA
 from sklearn.datasets import make_circles
-from scipy.spatial.distance import pdist, squareform
-from scipy import exp
-from scipy.linalg import eigh
-import numpy as np
 from sklearn.decomposition import KernelPCA
 
 # *Python Machine Learning 2nd Edition* by [Sebastian Raschka](https://sebastianraschka.com), Packt Publishing Ltd. 2017
@@ -922,8 +914,3 @@ def project_x(x_new, X, gamma, alphas, lambdas):
 
 
 
-
-
-
-
-

code/ch07/ch07.ipynb

@@ -1534,7 +1534,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": null,
+   "execution_count": 1,
    "metadata": {},
    "outputs": [
     {

code/ch07/ch07.py

@@ -5,20 +5,16 @@
 import math
 import numpy as np
 import matplotlib.pyplot as plt
-import numpy as np
 from sklearn.base import BaseEstimator
 from sklearn.base import ClassifierMixin
 from sklearn.preprocessing import LabelEncoder
 from sklearn.externals import six
 from sklearn.base import clone
 from sklearn.pipeline import _name_estimators
-import numpy as np
 import operator
 from sklearn import datasets
 from sklearn.preprocessing import StandardScaler
-from sklearn.preprocessing import LabelEncoder
 from sklearn.model_selection import train_test_split
-import numpy as np
 from sklearn.linear_model import LogisticRegression
 from sklearn.tree import DecisionTreeClassifier
 from sklearn.neighbors import KNeighborsClassifier 
@@ -29,13 +25,8 @@
 from itertools import product
 from sklearn.model_selection import GridSearchCV
 import pandas as pd
-from sklearn.preprocessing import LabelEncoder
-from sklearn.model_selection import train_test_split
 from sklearn.ensemble import BaggingClassifier
-from sklearn.tree import DecisionTreeClassifier
 from sklearn.metrics import accuracy_score
-import numpy as np
-import matplotlib.pyplot as plt
 from sklearn.ensemble import AdaBoostClassifier
 
 # *Python Machine Learning 2nd Edition* by [Sebastian Raschka](https://sebastianraschka.com), Packt Publishing Ltd. 2017

code/ch08/ch08.ipynb

@@ -1800,7 +1800,7 @@
      "output_type": "stream",
      "text": [
       "[NbConvertApp] Converting notebook ch08.ipynb to script\n",
-      "[NbConvertApp] Writing 24627 bytes to ch08.py\n"
+      "[NbConvertApp] Writing 24613 bytes to ch08.py\n"
      ]
     }
    ],

code/ch08/ch08.py

@@ -7,9 +7,6 @@
 import time
 import pyprind
 import pandas as pd
-import os
-import numpy as np
-import pandas as pd
 import numpy as np
 from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.feature_extraction.text import TfidfTransformer
@@ -21,19 +18,10 @@
 from sklearn.linear_model import LogisticRegression
 from sklearn.feature_extraction.text import TfidfVectorizer
 from sklearn.model_selection import GridSearchCV
-from sklearn.linear_model import LogisticRegression
-import numpy as np
 from sklearn.model_selection import StratifiedKFold
 from sklearn.model_selection import cross_val_score
-from sklearn.model_selection import GridSearchCV
-import numpy as np
-import re
-from nltk.corpus import stopwords
 from sklearn.feature_extraction.text import HashingVectorizer
 from sklearn.linear_model import SGDClassifier
-import pyprind
-import pandas as pd
-from sklearn.feature_extraction.text import CountVectorizer
 from sklearn.decomposition import LatentDirichletAllocation
 
 # *Python Machine Learning 2nd Edition* by [Sebastian Raschka](https://sebastianraschka.com), Packt Publishing Ltd. 2017
@@ -726,8 +714,3 @@ def get_minibatch(doc_stream, size):
 
 
 
-
-
-
-
-

code/ch10/ch10.ipynb

@@ -533,7 +533,7 @@
     "                 xticklabels=cols)\n",
     "\n",
     "plt.tight_layout()\n",
-    "plt.savefig('images/10_04.png', dpi=300)\n",
+    "# plt.savefig('images/10_04.png', dpi=300)\n",
     "plt.show()"
    ]
   },
@@ -712,7 +712,7 @@
     "plt.xlabel('Average number of rooms [RM] (standardized)')\n",
     "plt.ylabel('Price in $1000s [MEDV] (standardized)')\n",
     "\n",
-    "plt.savefig('images/10_06.png', dpi=300)\n",
+    "#plt.savefig('images/10_06.png', dpi=300)\n",
     "plt.show()"
    ]
   },
@@ -1715,7 +1715,7 @@
      "output_type": "stream",
      "text": [
       "[NbConvertApp] Converting notebook ch10.ipynb to script\n",
-      "[NbConvertApp] Writing 18556 bytes to ch10.py\n"
+      "[NbConvertApp] Writing 18559 bytes to ch10.py\n"
      ]
     }
    ],

code/ch10/ch10.py

@@ -9,13 +9,11 @@
 from sklearn.linear_model import LinearRegression
 from sklearn.linear_model import RANSACRegressor
 from sklearn.model_selection import train_test_split
-import numpy as np
 import scipy as sp
 from sklearn.metrics import r2_score
 from sklearn.metrics import mean_squared_error
 from sklearn.linear_model import Lasso
 from sklearn.linear_model import Ridge
-from sklearn.linear_model import Lasso
 from sklearn.linear_model import ElasticNet
 from sklearn.preprocessing import PolynomialFeatures
 from sklearn.tree import DecisionTreeRegressor
@@ -177,7 +175,7 @@
                  xticklabels=cols)
 
 plt.tight_layout()
-plt.savefig('images/10_04.png', dpi=300)
+# plt.savefig('images/10_04.png', dpi=300)
 plt.show()
 
 
@@ -262,7 +260,7 @@ def lin_regplot(X, y, model):
 plt.xlabel('Average number of rooms [RM] (standardized)')
 plt.ylabel('Price in $1000s [MEDV] (standardized)')
 
-plt.savefig('images/10_06.png', dpi=300)
+#plt.savefig('images/10_06.png', dpi=300)
 plt.show()
 
 

code/ch11/ch11.py

@@ -8,7 +8,6 @@
 from matplotlib import cm
 from sklearn.metrics import silhouette_samples
 import pandas as pd
-import numpy as np
 from scipy.spatial.distance import pdist, squareform
 from scipy.cluster.hierarchy import linkage
 from scipy.cluster.hierarchy import dendrogram

code/ch12/ch12.py

@@ -8,11 +8,6 @@
 import gzip
 import shutil
 import matplotlib.pyplot as plt
-import numpy as np
-import numpy as np
-import sys
-import numpy as np
-import matplotlib.pyplot as plt
 
 # *Python Machine Learning 2nd Edition* by [Sebastian Raschka](https://sebastianraschka.com), Packt Publishing Ltd. 2017
 # 
@@ -245,7 +240,7 @@ class NeuralNetMLP(object):
         Learning rate.
     shuffle : bool (default: True)
         Shuffles training data every epoch if True to prevent circles.
-    minibatche_size : int (default: 1)
+    minibatch_size : int (default: 1)
         Number of training samples per minibatch.
     seed : int (default: None)
         Random seed for initalizing weights and shuffling.

code/ch12/neuralnet.py

@@ -18,7 +18,7 @@ class NeuralNetMLP(object):
         Learning rate.
     shuffle : bool (default: True)
         Shuffles training data every epoch if True to prevent circles.
-    minibatche_size : int (default: 1)
+    minibatch_size : int (default: 1)
         Number of training samples per minibatch.
     seed : int (default: None)
         Random seed for initalizing weights and shuffling.