cleaning functions and function docs

Author: raviolli77

src/python/data_extraction.py

@@ -53,9 +53,9 @@
 
 # Create Training and Test Set ----------------------------------
 feature_space = breast_cancer.iloc[:,
- breast_cancer.columns != 'diagnosis']
+  breast_cancer.columns != 'diagnosis']
 feature_class = breast_cancer.iloc[:,
- breast_cancer.columns == 'diagnosis']
+  breast_cancer.columns == 'diagnosis']
 
 
 training_set, test_set, class_set, test_class_set = train_test_split(feature_space,

src/python/exploratory_analysis.py

@@ -13,24 +13,23 @@
 Exploratory Analysis
 """
 import helper_functions as hf
-import matplotlib.pyplot as plt 
-import seaborn as sns 
-
-breast_cancer = hf.breast_cancer
+from data_extraction import breast_cancer
+import matplotlib.pyplot as plt
+import seaborn as sns
 
 print('''
 ########################################
 ## DATA FRAME SHAPE AND DTYPES ##
 ########################################
 ''')
 
-print("Here's the dimensions of our data frame:\n", 
+print("Here's the dimensions of our data frame:\n",
 breast_cancer.shape)
 
-print("Here's the data types of our columns:\n", 
-breast_cancer.dtypes)
+print("Here's the data types of our columns:\n",
+breast_cancer.dtypes)
 
-print("Some more statistics for our data frame: \n", 
+print("Some more statistics for our data frame: \n",
 breast_cancer.describe())
 
 print('''
@@ -50,48 +49,48 @@
 # Scatterplot Matrix
 # Variables chosen from Random Forest modeling.
 
-cols = ['concave_points_worst', 'concavity_mean', 
-'perimeter_worst', 'radius_worst', 
+cols = ['concave_points_worst', 'concavity_mean',
+'perimeter_worst', 'radius_worst',
 'area_worst', 'diagnosis']
 
 sns.pairplot(breast_cancer,
 x_vars = cols,
 y_vars = cols,
-hue = 'diagnosis', 
-palette = ('Red', '#875FDB'), 
+hue = 'diagnosis',
+palette = ('Red', '#875FDB'),
 markers=["o", "D"])
 
 plt.title('Scatterplot Matrix')
 plt.show()
 plt.close()
 
 # Pearson Correlation Matrix
-corr = breast_cancer.corr(method = 'pearson') # Correlation Matrix
+corr = breast_cancer.corr(method = 'pearson') # Correlation Matrix
 f, ax = plt.subplots(figsize=(11, 9))
 
 # Generate a custom diverging colormap
-cmap = sns.diverging_palette(10, 275, as_cmap=True)
+cmap = sns.diverging_palette(10, 275, as_cmap=True)
 
 # Draw the heatmap with the mask and correct aspect ratio
 sns.heatmap(corr,
 cmap=cmap,
-square=True, 
-xticklabels=True, 
+square=True,
+xticklabels=True,
 yticklabels=True,
-linewidths=.5, 
-cbar_kws={"shrink": .5}, 
+linewidths=.5,
+cbar_kws={"shrink": .5},
 ax=ax)
 
 plt.title("Pearson Correlation Matrix")
 plt.yticks(rotation = 0)
-plt.xticks(rotation = 270)
+plt.xticks(rotation = 270)
 plt.show()
 plt.close()
 
 # BoxPlot
 hf.plot_box_plot(breast_cancer, 'Pre-Processed', (-.05, 50))
 
-# Normalizing data 
+# Normalizing data
 breast_cancer_norm = hf.normalize_data_frame(breast_cancer)
 
 # Visuals relating to normalized data to show significant difference
@@ -103,4 +102,4 @@
 
 print(breast_cancer_norm.describe())
 
-hf.plot_box_plot(breast_cancer_norm, 'Transformed', (-.05, 1.05))
+hf.plot_box_plot(breast_cancer_norm, 'Transformed', (-.05, 1.05))