aws-samples / churn-prediction-with-text-and-interpretability
Conditional Complexity

The distribution of complexity of units (measured with McCabe index).

Intro
  • Conditional complexity (also called cyclomatic complexity) is a term used to measure the complexity of software. The term refers to the number of possible paths through a program function. A higher value ofter means higher maintenance and testing costs (infosecinstitute.com).
  • Conditional complexity is calculated by counting all conditions in the program that can affect the execution path (e.g. if statement, loops, switches, and/or operators, try and catch blocks...).
  • Conditional complexity is measured at the unit level (methods, functions...).
  • Units are classified in four categories based on the measured McCabe index: 1-5 (simple units), 6-10 (medium complex units), 11-25 (complex units), 26+ (very complex units).
Learn more...
Conditional Complexity Overall
  • There are 34 units with 181 lines of code in units (24.2% of code).
    • 0 very complex units (0 lines of code)
    • 0 complex units (0 lines of code)
    • 0 medium complex units (0 lines of code)
    • 1 simple units (15 lines of code)
    • 33 very simple units (166 lines of code)
0% | 0% | 0% | 8% | 91%
Legend:
51+
26-50
11-25
6-10
1-5
Alternative Visuals
Conditional Complexity per Extension
51+
26-50
11-25
6-10
1-5
py0% | 0% | 0% | 8% | 91%
Conditional Complexity per Logical Component
primary logical decomposition
51+
26-50
11-25
6-10
1-5
scripts0% | 0% | 0% | 8% | 91%
Most Complex Units
Top 20 most complex units
Unit# linesMcCabe index# params
def get_keywords()
in scripts/interpret.py
 15 6 1
def map_to_orig_tok()
in scripts/interpret.py
 8 3 2
def train_xgb()
in scripts/interpret.py
 21 3 0
def transform()
in scripts/preprocess.py
 6 2 2
def __init__()
in scripts/train.py
 6 1 3
def forward()
in scripts/train.py
 10 1 3
def train()
in scripts/train.py
 5 1 0
def test()
in scripts/train.py
 3 1 0
def get_train_assets()
in scripts/train.py
 1 1 0
def predict()
in scripts/train.py
 3 1 0
def plot_train_stats()
in scripts/train.py
 1 1 0
def plot_pr_curve()
in scripts/train.py
 3 1 0
def plot_roc_curve()
in scripts/train.py
 3 1 0
def create_joint_dataset()
in scripts/create_dataset.py
 3 1 0
def __init__()
in scripts/preprocess.py
 3 1 2
def fit()
in scripts/preprocess.py
 2 1 3
def extract_labels()
in scripts/preprocess.py
 3 1 0
def convert_label()
in scripts/preprocess.py
 2 1 0
def extract_numerical_features()
in scripts/preprocess.py
 3 1 0
def extract_categorical_features()
in scripts/preprocess.py
 3 1 0