diff --git a/main.py b/main.py
index 0e743bfeb9f9e4a54ac4ac2457d47d59ca2417c1..582912c51b2945da9552e4d3245ee3d52ad9475e 100644
--- a/main.py
+++ b/main.py
@@ -6,7 +6,7 @@ Covers basic statistical measurements in data mining.
# User Imports.
from resources import logging as init_logging
-from resources.stat_functions import Aggregations
+from resources.stat_functions import Aggregations, Normalizations
# Initialize Logger.
@@ -20,6 +20,7 @@ def main():
logger.info('Starting main()')
calc_part_1()
+ calc_part_2()
def calc_part_1():
@@ -44,6 +45,50 @@ def calc_part_1():
# logger.info(student_array[len(student_array) - 1])
+ # Get aggregation values.
+ id_agg = Aggregations.all(student_array, 'id', display=False)
+ midterm_agg = Aggregations.all(student_array, 'midterm', display=False)
+ final_agg = Aggregations.all(student_array, 'final', display=False)
+
+ # Display results.
+ logger.info('')
+ logger.info('Id Analysis Results (for debugging):')
+ for key, item in id_agg.items():
+ logger.info(' {0}: {1}'.format(key, item))
+ logger.info('')
+ logger.info('Midterm Analysis Results:')
+ for key, item in midterm_agg.items():
+ logger.info(' {0}: {1}'.format(key, item))
+ logger.info('')
+ logger.info('Final Analysis Results:')
+ for key, item in final_agg.items():
+ logger.info(' {0}: {1}'.format(key, item))
+ logger.info('')
+
+
+def calc_part_2():
+ student_array = []
+
+ # Open file.
+ with open('./documents/data.online.scores.txt', 'r') as student_scores_file:
+ # Read in each line and save to our struct.
+ for line in student_scores_file:
+ # Split on tabs.
+ split_line = line.strip().split('\t')
+
+ # Save to struct.
+ student_array.append({
+ 'id': int(split_line[0]),
+ 'midterm': int(split_line[1]),
+ 'final': int(split_line[2]),
+ })
+
+ # logger.info(student_array[len(student_array) - 1])
+
+ # Normalize data.
+ student_array = Normalizations.z_score(student_array)
+
+ # Get aggregation values.
id_agg = Aggregations.all(student_array, 'id', display=False)
midterm_agg = Aggregations.all(student_array, 'midterm', display=False)
final_agg = Aggregations.all(student_array, 'final', display=False)
diff --git a/resources/stat_functions.py b/resources/stat_functions.py
index 8139734e216eeac06db19e9271c0f9648cd281ff..c89828366848248c328c739a487c77cc16cdfbff 100644
--- a/resources/stat_functions.py
+++ b/resources/stat_functions.py
@@ -7,7 +7,7 @@ Larger datasets (where efficiency and runtime matter) should probably instead us
"""
# System Imports.
-import numpy
+import copy, numpy
from scipy import stats
# User Imports.
@@ -257,3 +257,112 @@ class Aggregations():
# Return aggregation.
return Aggregations.median(struct[int(len(struct) / 2):], attribute, display=False)
+
+
+class Normalizations():
+ @staticmethod
+ def min_max(struct, new_min, new_max, attribute=None, display=True):
+ """
+ Normalizes the attribute (key) for the provided dict.
+ If no attribute is provided, then normalizes all attributes in provided dict.
+ :param struct: Data structure to normalize on.
+ :param new_min: New minimum to use for attribute.
+ :param new_max: New maximum to use for attribute.
+ :param attribute: Attribute to normalize. If left empty, then all attributes are normalized.
+ :param display: Bool indicating if helper text should display.
+ :return: A copy of the provided structure, with the given attribute normalized.
+ """
+ # Copy struct so we don't override original values.
+ struct = copy.deepcopy(struct)
+
+ # Check what attributes to normalize.
+ if attribute is None:
+ # Normalize all attributes.
+
+ # Examine all attributes.
+ for attribute in struct[0].keys():
+ if display:
+ logger.info('Running Min-Max Normalization on "{0}".'.format(attribute))
+
+ # Get relevant aggregations.
+ old_min = Aggregations.min(struct, attribute, display=False)
+ old_max = Aggregations.max(struct, attribute, display=False)
+
+ # Loop through and normalize all values of attribute.
+ for index in range(len(struct)):
+ old_value = struct[index][attribute]
+ new_value = ((old_value - old_min) / (old_max - old_min)) * (new_max - new_min) + new_min
+ struct[index][attribute] = new_value
+ else:
+ # Normalize single provided attribute.
+ if display:
+ logger.info('Running Min-Max Normalization on "{0}".'.format(attribute))
+
+ # Get relevant aggregations.
+ old_min = Aggregations.min(struct, attribute, display=False)
+ old_max = Aggregations.max(struct, attribute, display=False)
+
+ # Loop through and normalize all values of attribute.
+ for index in range(len(struct)):
+ old_value = struct[index][attribute]
+ new_value = ( (old_value - old_min) / (old_max - old_min) ) * (new_max - new_min) + new_min
+ struct[index][attribute] = new_value
+
+ # Return normalized struct.
+ return struct
+
+ @staticmethod
+ def zero_mean(struct, attribute=None, display=True):
+ """
+ Normalizes the attribute (key) for the provided dict.
+ If no attribute is provided, then normalizes all attributes in provided dict.
+ :param struct: Data structure to normalize on.
+ :param attribute: Attribute to normalize. If left empty, then all attributes are normalized.
+ :param display: Bool indicating if helper text should display.
+ :return: A copy of the provided structure, with the given attribute normalized.
+ """
+ # Copy struct so we don't override original values.
+ struct = copy.deepcopy(struct)
+
+ # Check what attributes to normalize.
+ if attribute is None:
+ # Normalize all attributes.
+
+ # Examine all attributes.
+ for attribute in struct[0].keys():
+ if display:
+ logger.info('Running Zero-Mean Normalization on "{0}".'.format(attribute))
+
+ # Get relevant aggregations.
+ mean = Aggregations.mean(struct, attribute, display=False)
+ standard_deviation = Aggregations.standard_deviation(struct, attribute, display=False)
+
+ # Loop through and normalize all values of attribute.
+ for index in range(len(struct)):
+ old_value = struct[index][attribute]
+ new_value = (old_value - mean) / standard_deviation
+ struct[index][attribute] = new_value
+ else:
+ # Normalize single provided attribute.
+ if display:
+ logger.info('Running Zero-Mean Normalization on "{0}".'.format(attribute))
+
+ # Get relevant aggregations.
+ mean = Aggregations.mean(struct, attribute, display=False)
+ standard_deviation = Aggregations.standard_deviation(struct, attribute, display=False)
+
+ # Loop through and normalize all values of attribute.
+ for index in range(len(struct)):
+ old_value = struct[index][attribute]
+ new_value = (old_value - mean) / standard_deviation
+ struct[index][attribute] = new_value
+
+ # Return normalized struct.
+ return struct
+
+ @staticmethod
+ def z_score(struct, attribute=None, display=True):
+ """
+ Alias for "zero_mean" normalization.
+ """
+ return Normalizations.zero_mean(struct, attribute=attribute, display=display)