def main_function(data_frame):
get_details(data_frame)
print("Class count\n", data_frame.groupby(SECOND_LEVEL_TARGET).size())
# Impute missing values
data_frame = impute_missing_values(data_frame, "most_frequent")
print(data_frame.head(20))
print(data_frame.isnull().sum().sum())
# Get the correlation matrix
# get_feature_correlations(data_frame, plot=True, return_resulst=True)
# Check if duplicate records exist
is_duplicated = check_duplicates(data_frame)
# Drop duplicate records if exist
if is_duplicated:
data_frame.drop_duplicates(inplace=True)
print("Dropped duplicate records. Size after dropping duplicates: ",
data_frame.shape)
# One Hot Encoding
columns_to_encode = [
'sex', 'histologic-type', 'bone', 'bone-marrow', 'lung', 'pleura',
'peritoneum', 'liver', 'brain', 'skin', 'neck', 'supraclavicular',
'axillar', 'mediastinum', 'abdominal', 'small-intestine'
]
data_frame = perform_one_hot_encoding(data_frame, columns_to_encode)
# Pre-prcoessed dataset
pre_processed_data = data_frame
# Top Level Classifier - classify by region
classify_by_region(pre_processed_data)
# Create balanced datasets for the second level
# create_separate_datasets(pre_processed_data)
# #
# upper_region_classifier()
#
# thoracic_region_classifier()
#
ip_region_classifier()
#
ep_region_classifier()
figsize(8, 8)
# Density plot of the final predictions and the test values
sns.kdeplot(data_frame['brain'], label='original')
sns.kdeplot(data_frame2['brain'], label='Synthetic')
# Label the plot
plt.xlabel('Primary Tumor Sites')
plt.ylabel('Density')
plt.title('Test Values and Predictions')
plt.show()
######################################################### EDA ########################################################
print("\n\n!!!!!!!!!!!!!!!!!!!!!!! EDA !!!!!!!!!!!!!!!!!!!!!!!!\n")
get_details(data_frame)
# visualize_class_distribution(data_frame, "class")
# visualise_feature_distribution(data_frame)
is_duplicated = check_duplicates(data_frame)
################################################### Data Preprocessing ###############################################
print(
"\n\n!!!!!!!!!!!!!!!!!!!!!!! DATA PREPROCESSING !!!!!!!!!!!!!!!!!!!!!!!!\n"
)
# Impute missing values
data_frame = impute_missing_values(data_frame, "most_frequent")
# Drop duplicate records if exist
if is_duplicated:
data_frame.drop_duplicates(inplace=True)
print("Dropped duplicate records. Size after dropping duplicates: ",
data_frame.shape)
