def svc_drop_miss(file, encoding):
#Creates a new dataframe that is the original bcdata dataframe with all rows with missing values dropped
bcdata = clean_data.drop_miss(file, encoding)
#Subsets the above dataframe, split into the bare nuclei values and all other attribute values
all_data = bcdata.drop(['Sample ID', 'Class label'], axis=1)
class_data = bcdata['Class label']
#Split the subset data (bare nuclei and all other attributes) into training and testing sets
all_train, all_test, class_train, class_test = train_test_split(
all_data, class_data, test_size=0.20)
#Instantiate the SVC model using linear kernel
svclassifier = SVC(kernel='linear')
#Fit SVC model to the training data
svclassifier.fit(all_train, class_train)
#Use the SVC model fit to the training data to predict the class label of the test set
svm_y_pred = svclassifier.predict(all_test)
#Create a list of tuples, where each tuple is a side-by-side comparison of the actual class label, compared with the predicted class
#label of the SVM
test_v_pred = zip(class_test.values, svm_y_pred)
print(test_v_pred)
#Determine the approximate accuracy of the SVM model fit to this data
#Initialize a count that will track the number of times the model predicts an inaccurate class label
count = 0
#Iterate through the list of zipped tuples
for tup in test_v_pred:
#If the first item of the tuple does not equal the second item, increment the count up by 1
if tup[0] != tup[1]:
count += 1
return class_test.values, svm_y_pred, count
def color_map(file, encoding):
drop_miss = clean_data.drop_miss(file, encoding)
bcdata = drop_miss.drop(['Class label', 'Sample ID'], axis=1)
#Creates a segmented line chart/color map. Each value across the x-axis represents one attribute
plt.imshow(bcdata, aspect='auto')
plt.colorbar()
plt.xlabel('BC Data Attributes')
plt.ylabel('Patient Record')
plt.show()
def fill_w_avg(file, encoding): bcdata_no_miss = clean_data.drop_miss(file, encoding) bcdata_w_miss = clean_data.miss_to_nan(file, encoding) print(bcdata_w_miss['Bare nuclei'].value_counts()) mean = int(bcdata_no_miss['Bare nuclei'].mean()) bcdata = bcdata_w_miss.fillna(mean) print(zip(bcdata_w_miss['Bare nuclei'].value_counts().values, bcdata['Bare nuclei'].value_counts().values)) return bcdata
def pair_plot(file, encoding):
bcdata = clean_data.drop_miss(file, encoding)
bcdata = bcdata.drop(['Sample ID', 'Class label'], axis=1)
print(bcdata)
#Instantiate a pairplot for all data except for Sample ID
sns.pairplot(bcdata,
kind='reg',
plot_kws={
'line_kws': {
'color': 'red'
},
'scatter_kws': {
'alpha': 0.1
}
})
plt.show()
def statsmod_lin_reg_predict(file, encoding):
results = statsmod_lin_reg(file, encoding)[0]
miss_to_nan = statsmod_lin_reg(file, encoding)[1]
all_given = given_to_impute(file, encoding)
known_to_predict = clean_data.subset_miss_data_x(file, encoding)
#Predict the bare nuclei values (that are already known) using the values across the other attributes
bn_known_preds = results.predict(all_given)
#Create a scatter plot of the known bare nuclei values, and the bare nuclei values that were predicted by the model
plt.scatter(clean_data.drop_miss(file, encoding)['Bare nuclei'],
bn_known_preds,
alpha=.1)
#Label the x-axis of the scatter plot
plt.xlabel('Actual Bare nuclei')
#Label the y-axis of the scatter plot
plt.ylabel('Predicted Bare nuclei')
#Invoke the visualization of the scatter plot
plt.show()
#Predict the missing bare nuclei values using the known values of the other attributes
bn_unknown_preds = results.predict(known_to_predict)
print(bn_unknown_preds)
#Create a subset of the previously created dataframe, with all missing values dropped, that includes only the records
#with a malignant diagnosis
mal_cases = miss_to_nan[miss_to_nan['Class label'] == 4]
#Among the records with malignant diagnosis, create a scatter plot of the normal nucleoli values and the bare nuclei values
#to determine if there appears to be any correlation
plt.scatter(mal_cases['Normal nucleoli'],
mal_cases['Bare nuclei'],
alpha=.1)
plt.xlabel('Normal nucleoli')
plt.ylabel('Bare nuclei')
plt.show()
def fill_w_mode(file, encoding): #Create a dataframe with all the rows with missing values dropped bcdata_no_miss = clean_data.drop_miss(file, encoding) #Create a dataframe with all missing values replaced with the NaN datatype bcdata_w_miss = clean_data.miss_to_nan(file, encoding) #Print out a series that displays each possible value of bare nuclei, and the frequency of each value print(type(bcdata_w_miss['Bare nuclei'].value_counts())) #Create a numpy array that lists every value of the bare nuclei attribute that has a mode frequency mode = bcdata_no_miss['Bare nuclei'].mode().values #Creates a new dataframe with all of the missing values filled in with the previously determined' #mode value bcdata = bcdata_w_miss.fillna(mode[0]) #Print out a list of tuples, each tuple representing each value of the bare nuclei attribute #containing the original frequency of that value and the adjusted frequency following replaced values print(zip(bcdata_w_miss['Bare nuclei'].value_counts().values, bcdata['Bare nuclei'].value_counts().values)) return bcdata