diff --git a/.devcontainer/devcontainer.json b/.devcontainer/devcontainer.json
index 0c5c160674bc408afdab31b9b64cf67d14027d3c..07fdc2b2e3353714c87e4bdcda39db7657275e5c 100644
--- a/.devcontainer/devcontainer.json
+++ b/.devcontainer/devcontainer.json
@@ -14,7 +14,8 @@
}
},
"containerEnv": {
- "SHELL": "/bin/bash"
+ "SHELL": "/bin/bash",
+ "MPLBACKEND": "Agg"
},
"remoteEnv": {
"PATH": "/home/vscode/.local/bin:${containerEnv:PATH}"
diff --git a/.gitlab-ci.yml b/.gitlab-ci.yml
index 9aeb88aa8b2be32a2e4ca920fddfa5d5881cb9a5..540ac63ddff3d1258c88aa227cc9fa2c9445af46 100644
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -19,3 +19,12 @@ correlation_analysis:
- out/
script:
- vqcfim correlation-analysis --train-data dataset/InjectionMolding_Train.csv --out out --correlation-threshold 0.9
+
+best_single_feature_regression:
+ extends: .run_script
+ artifacts:
+ expire_in: 1d
+ paths:
+ - out/
+ script:
+ - vqcfim best-single-feature-regression --train-data dataset/InjectionMolding_Train.csv --out out --target 'mass' --p-value-threshold 0.05
diff --git a/.vscode/launch.json b/.vscode/launch.json
index d478b9d80d1985421ebfa0fafb66f7d55d20b1da..1c202b64322dfd0aec4c5265a4c968a619c3e328 100644
--- a/.vscode/launch.json
+++ b/.vscode/launch.json
@@ -19,6 +19,24 @@
"-c",
"0.9"
]
+ },
+ {
+ "name": "Python Debugger: Best Single Feature Regression",
+ "type": "debugpy",
+ "request": "launch",
+ "program": "${workspaceFolder}/src/app.py",
+ "console": "integratedTerminal",
+ "args": [
+ "best-single-feature-regression",
+ "-t",
+ "dataset/InjectionMolding_Train.csv",
+ "--target",
+ "mass",
+ "-o",
+ "out",
+ "--p-value-threshold",
+ "0.05"
+ ]
}
]
}
diff --git a/pyproject.toml b/pyproject.toml
index 68b42c6b58d0fcc098daa6808d7521e90ead2593..96bd934250ea9c5bf9faf748e62552449dd54356 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -5,7 +5,8 @@ description = "Virtual Quality Control for Injection Molding"
dependencies = [
"pandas >= 2.2.3, < 3.0.0",
"seaborn >= 0.13.2, < 1.0.0",
- "matplotlib >= 3.9.2, < 4.0.0"
+ "matplotlib >= 3.9.2, < 4.0.0",
+ "statsmodels >= 0.14.4, < 1.0.0",
]
maintainers = [
{name = "Andri Joos"},
diff --git a/src/app.py b/src/app.py
index a8ee507f1ccbe1798131a72c20e056b21eaa4c41..328a6be30c5b0169abd5607afef5f777951ed502 100644
--- a/src/app.py
+++ b/src/app.py
@@ -5,6 +5,7 @@ import seaborn as sns
import matplotlib.pyplot as plt
import math
from typing import List, Tuple
+import statsmodels.api as sm
TRAIN_DATA_ARG = '--train-data'
TRAIN_DATA_ARG_SHORT = '-t'
@@ -14,6 +15,12 @@ DEFAULT_OUT_DIR = 'out/'
CORRELATION_THRESHOLD_ARG = '--correlation-threshold'
CORRELATION_THRESHOLD_ARG_SHORT = '-c'
DEFAULT_CORRELATION_THRESHOLD = 0.9
+TARGET_ARG = '--target'
+P_VALUE_THRESHOLD_ARG = '--p-value-threshold'
+DEFAULT_P_VALUE_THRESHOLD = 0.05
+
+PVALUE_COLUMN_NAME = 'p-value'
+RSQUARED_COLUMN_NAME = 'R^2'
def ensure_directory(directory: Path):
directory.mkdir(parents=True, exist_ok=True)
@@ -25,7 +32,7 @@ def correlation_analysis(train_data_file: Path, out_dir: Path, correlation_thres
# Display correlation matrix
correlation_matrix = train_data.corr()
plt.figure(figsize=(10, 8))
- sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm')
+ sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', vmin=-1, vmax=1)
plt.title('Correlation Matrix')
ensure_directory(out_dir)
@@ -55,16 +62,87 @@ def correlation_analysis(train_data_file: Path, out_dir: Path, correlation_thres
with open(correlations_file, 'w') as f:
f.writelines(correlations)
+def single_feature_regression(data: pd.DataFrame, feature: str, target: str):
+ X = sm.add_constant(data[[feature]]) # Add constant for intercept
+ y = data[target]
+ model = sm.OLS(y, X).fit()
+ return model.pvalues.iloc[1], model.rsquared
+
+def best_single_feature_regression(train_data_file: Path, target: str, p_value_threshold: float, out_dir: Path):
+ train_data = pd.read_csv(train_data_file)
+ features = train_data.columns
+ features = features.drop(target)
+
+ evaluated_features = pd.DataFrame({
+ PVALUE_COLUMN_NAME: pd.Series(dtype='float'),
+ RSQUARED_COLUMN_NAME: pd.Series(dtype='float'),
+ })
+ for feature in features:
+ pvalue, rsquared = single_feature_regression(train_data, feature, target)
+ evaluated_features.loc[feature] = {PVALUE_COLUMN_NAME: pvalue, RSQUARED_COLUMN_NAME: rsquared}
+
+ print('Evaluated features')
+ print(evaluated_features)
+
+ plt.figure(figsize=(1.75, 4.8))
+ evaluated_pvalues = evaluated_features[[PVALUE_COLUMN_NAME]]
+ sns.heatmap(evaluated_pvalues, annot=True, cmap='coolwarm', vmin=0, vmax=1)
+
+ ensure_directory(out_dir)
+ evaluated_pvalues_file_path = out_dir / "evaluated_pvalues.png"
+ plt.savefig(evaluated_pvalues_file_path, bbox_inches='tight')
+
+ plt.figure(figsize=(1.75, 4.8))
+ evaluated_rsquares = evaluated_features[[RSQUARED_COLUMN_NAME]]
+ sns.heatmap(evaluated_rsquares, annot=True, cmap='coolwarm', vmin=0, vmax=1)
+
+ ensure_directory(out_dir)
+ evaluated_rsquares_file_path = out_dir / "evaluated_rsquares.png"
+ plt.savefig(evaluated_rsquares_file_path, bbox_inches='tight')
+
+ possible_features = evaluated_features.where(evaluated_features[PVALUE_COLUMN_NAME] < p_value_threshold).dropna()
+ possible_features = possible_features.sort_values(RSQUARED_COLUMN_NAME, ascending=False)
+
+ print()
+ print('Features matching p-value-threshold')
+ print(possible_features)
+
+ best_feature: pd.Series = None
+ if possible_features.shape[0] > 0:
+ best_feature = possible_features.iloc[0]
+ else:
+ print('No feature meets all criteria')
+ return
+
+ print()
+ print('Best Feature')
+ print(best_feature)
+
+ ensure_directory(out_dir)
+ best_feature_file = out_dir / 'best_feature.txt'
+ with open(best_feature_file, 'w') as f:
+ f.write(f'''Name: {best_feature.name}
+p-value: {best_feature[PVALUE_COLUMN_NAME]}
+R^2: {best_feature[RSQUARED_COLUMN_NAME]}
+''')
+
def main():
argument_parser = ArgumentParser('vqcfim', description='Virtual Quality Control for Injection Molding')
subparsers = argument_parser.add_subparsers(title='action')
- correlation_analysis_subparser = subparsers.add_parser('correlation-analysis', aliases=['c'], description='Gets variables with correlation coefficients >= 0.9')
+ correlation_analysis_subparser = subparsers.add_parser('correlation-analysis', aliases=['ca'], description='Gets variables with correlation coefficients >= --correlation-coefficient')
correlation_analysis_subparser.add_argument(TRAIN_DATA_ARG, TRAIN_DATA_ARG_SHORT, action='store', type=Path, required=True)
correlation_analysis_subparser.add_argument(OUT_DIR_ARG, OUT_DIR_ARG_SHORT, action='store', type=Path, required=False, default=DEFAULT_OUT_DIR)
correlation_analysis_subparser.add_argument(CORRELATION_THRESHOLD_ARG, CORRELATION_THRESHOLD_ARG_SHORT, action='store', type=float, required=False, default=DEFAULT_CORRELATION_THRESHOLD)
correlation_analysis_subparser.set_defaults(func=lambda train_data, out, correlation_threshold, func: correlation_analysis(train_data, out, correlation_threshold))
+ best_single_feature_regression_subparser = subparsers.add_parser('best-single-feature-regression', aliases=['bsfr'], description='Evaluates the best single feature regression feature from the dataset')
+ best_single_feature_regression_subparser.add_argument(TRAIN_DATA_ARG, TRAIN_DATA_ARG_SHORT, action='store', type=Path, required=True)
+ best_single_feature_regression_subparser.add_argument(TARGET_ARG, action='store', type=str, required=True)
+ best_single_feature_regression_subparser.add_argument(OUT_DIR_ARG, OUT_DIR_ARG_SHORT, action='store', type=Path, required=False, default=DEFAULT_OUT_DIR)
+ best_single_feature_regression_subparser.add_argument(P_VALUE_THRESHOLD_ARG, action='store', type=float, required=False, default=DEFAULT_P_VALUE_THRESHOLD)
+ best_single_feature_regression_subparser.set_defaults(func=lambda train_data, target, out, p_value_threshold, func: best_single_feature_regression(train_data, target, p_value_threshold, out))
+
parsed_args = argument_parser.parse_args()
args = vars(parsed_args)
parsed_args.func(**args)