segments py3

projects/customer_segments/customer_segments.ipynb

@@ -36,9 +36,7 @@
   {
    "cell_type": "code",
    "execution_count": null,
-   "metadata": {
-    "collapsed": true
-   },
+   "metadata": {},
    "outputs": [],
    "source": [
     "# Import libraries necessary for this project\n",
@@ -56,9 +54,9 @@
     "try:\n",
     "    data = pd.read_csv(\"customers.csv\")\n",
     "    data.drop(['Region', 'Channel'], axis = 1, inplace = True)\n",
-    "    print \"Wholesale customers dataset has {} samples with {} features each.\".format(*data.shape)\n",
+    "    print(\"Wholesale customers dataset has {} samples with {} features each.\".format(*data.shape))\n",
     "except:\n",
-    "    print \"Dataset could not be loaded. Is the dataset missing?\""
+    "    print(\"Dataset could not be loaded. Is the dataset missing?\")"
    ]
   },
   {
@@ -104,7 +102,7 @@
     "\n",
     "# Create a DataFrame of the chosen samples\n",
     "samples = pd.DataFrame(data.loc[indices], columns = data.keys()).reset_index(drop = True)\n",
-    "print \"Chosen samples of wholesale customers dataset:\"\n",
+    "print(\"Chosen samples of wholesale customers dataset:\")\n",
     "display(samples)"
    ]
   },
@@ -330,7 +328,7 @@
     "    step = None\n",
     "    \n",
     "    # Display the outliers\n",
-    "    print \"Data points considered outliers for the feature '{}':\".format(feature)\n",
+    "    print(\"Data points considered outliers for the feature '{}':\".format(feature))\n",
     "    display(log_data[~((log_data[feature] >= Q1 - step) & (log_data[feature] <= Q3 + step))])\n",
     "    \n",
     "# OPTIONAL: Select the indices for data points you wish to remove\n",
@@ -704,7 +702,7 @@
    "source": [
     "# Display the predictions\n",
     "for i, pred in enumerate(sample_preds):\n",
-    "    print \"Sample point\", i, \"predicted to be in Cluster\", pred"
+    "    print(\"Sample point\", i, \"predicted to be in Cluster\", pred)"
    ]
   },
   {
@@ -820,21 +818,21 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 2",
+   "display_name": "Python 3",
    "language": "python",
-   "name": "python2"
+   "name": "python3"
   },
   "language_info": {
    "codemirror_mode": {
     "name": "ipython",
-    "version": 2
+    "version": 3
    },
    "file_extension": ".py",
    "mimetype": "text/x-python",
    "name": "python",
    "nbconvert_exporter": "python",
-   "pygments_lexer": "ipython2",
-   "version": "2.7.12"
+   "pygments_lexer": "ipython3",
+   "version": "3.6.2"
   }
  },
  "nbformat": 4,

projects/customer_segments/visuals.py

@@ -25,7 +25,7 @@ def pca_results(good_data, pca):
 	dimensions = dimensions = ['Dimension {}'.format(i) for i in range(1,len(pca.components_)+1)]
 
 	# PCA components
-	components = pd.DataFrame(np.round(pca.components_, 4), columns = good_data.keys())
+	components = pd.DataFrame(np.round(pca.components_, 4), columns = list(good_data.keys()))
 	components.index = dimensions
 
 	# PCA explained variance
@@ -132,7 +132,7 @@ def channel_results(reduced_data, outliers, pca_samples):
 	try:
 	    full_data = pd.read_csv("customers.csv")
 	except:
-	    print "Dataset could not be loaded. Is the file missing?"
+	    print("Dataset could not be loaded. Is the file missing?")       
 	    return False
 
 	# Create the Channel DataFrame