mirror of
https://github.com/kuhyx/WUT_Computer_Science.git
synced 2026-11-10 22:47:09 +01:00
Krzysztof kuhy Rudnicki
cc06bc0cd8
749 findings across six labs and two projects. The mechanical half was scripted; everything below is what the scripts got wrong or could not do, and how it was caught. Three regressions I introduced and then found by RUNNING the code, not by reading it: - Converting print() to logger.info() made the programs SILENT. logging's last-resort handler only emits WARNING and above, so with no basicConfig call `lab2/main.py -t 1 1` printed nothing at all. Fifteen files across the repo now configure logging where they log. - The same conversion dropped `end=""`. lab2 draws its board one square at a time and lab1 draws the maze one cell at a time; both came out one glyph per line. Those thirteen call sites are sys.stdout.write again, and the rendered board now diffs byte-identically against the pre-change output. - The B007 fix renamed `col` to `_col` in the FIRST loop it matched, which was print_letters -- where the variable IS used. That would have been a NameError on the first call. And one the scripts caused silently: annotating 110 signatures dropped the DEFAULT VALUES from 22 of them, so `preprocessing(a, b, USER_THRESHOLD, ANIME_THRESHOLD)` would have raised TypeError. Every signature is now diffed against the pre-change version, name by name and default by default: zero mismatches. Real defects the lint surfaced: - `alpha_beta` ended with an unreachable `return None` that violated its own return type. Its maximising and minimising halves were mirror images, so they are one `_search_branch` now (C901 11 -> ok). - `get_data`'s `gpu` switch, `predict`'s `auto`, `create_model`'s `rows_number` and five of `preprocess_model_predict`'s fifteen parameters were never read. Gone, with their call sites. - np.random.* -> Generator throughout (NPY002), `.values` -> `.to_numpy()`, `datetime.now()` with a tzinfo, `inplace=True` removed, `except:` given a type, `random.*` -> `SystemRandom` (S311). - print_board's three nested helpers became methods (C901 17 -> ok); user_input's nine-branch if-ladder became a table (C901 12 -> ok). Verification, all by running: lab1 `-t` and lab2 `-t 1 1` produce output byte-identical to the pre-change code; lab2's rendered 8x8 board diffs clean; lab3's argument parsing returns the same dict for the same argv; lab4 fails identically before and after (no sklearn here). Also included: the logging configuration for NLP, MOM and ECRYPT_PROJECT, which had the same silence bug. Repo-wide: 2,775 findings -> 1,883. Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_0172dj34FDpao6wsix8ZuCzE
118 lines
3.5 KiB
Python
Executable File
118 lines
3.5 KiB
Python
Executable File
#!/usr/bin/env python3
|
|
"""Program that predicts wine quality based on variant2.csv data."""
|
|
|
|
import logging
|
|
|
|
import matplotlib.pyplot as plt
|
|
import numpy as np
|
|
import pandas as pd
|
|
import seaborn as sns
|
|
from sklearn.linear_model import LogisticRegression
|
|
from sklearn.metrics import accuracy_score, f1_score, mean_squared_error
|
|
from sklearn.model_selection import train_test_split
|
|
from sklearn.preprocessing import StandardScaler
|
|
|
|
logger = logging.getLogger(__name__)
|
|
logging.basicConfig(format="%(message)s", level=logging.INFO)
|
|
|
|
|
|
class LinearRegression:
|
|
"""Implements Linear regression method."""
|
|
|
|
def __init__(self) -> None:
|
|
"""Start with no fitted coefficients."""
|
|
self.theta = None
|
|
|
|
def fit(self, x_values: object, y_values: object) -> None:
|
|
"""Fit linear regression model to our training data."""
|
|
# Add a column of ones to X for the intercept term
|
|
x_values = np.concatenate((np.ones((x_values.shape[0], 1)), y_values), axis=1)
|
|
|
|
# Compute the least squares solution using the normal equation
|
|
self.theta = (
|
|
np.linalg.inv(x_values.T.dot(x_values)).dot(x_values.T).dot(y_values)
|
|
)
|
|
|
|
def predict(self, x_values: object) -> object:
|
|
"""Predict the target values for the given inputs.
|
|
|
|
Uses the trained linear regression
|
|
|
|
model.
|
|
"""
|
|
# Add a column of ones to X for the intercept term
|
|
x_values = np.concatenate((np.ones((x_values.shape[0], 1)), x_values), axis=1)
|
|
|
|
# Make predictions using the learned weights
|
|
return x_values.dot(self.theta)
|
|
|
|
def score(self, x_values: object, y_values: object) -> float:
|
|
"""Compute the R-squared score of the model.
|
|
|
|
Measured on our test"
|
|
" data.
|
|
"""
|
|
y_predicted = self.predict(x_values)
|
|
ss_res = np.sum((y_values - y_predicted) ** 2)
|
|
ss_tot = np.sum((y_values - np.mean(y_values)) ** 2)
|
|
return 1 - (ss_res / ss_tot)
|
|
|
|
|
|
wine_df = pd.read_csv("variant2.csv")
|
|
wine_df.head()
|
|
wine_df.describe()
|
|
wine_df.info()
|
|
|
|
|
|
X = wine_df.iloc[:, :-1].to_numpy()
|
|
y = wine_df.iloc[:, -1].to_numpy()
|
|
|
|
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=0)
|
|
|
|
scaler = StandardScaler()
|
|
X_train = scaler.fit_transform(X_train)
|
|
X_test = scaler.transform(X_test)
|
|
regressor = LinearRegression()
|
|
regressor.fit(X_train, y_train)
|
|
|
|
y_pred = regressor.predict(X_test)
|
|
|
|
mse = mean_squared_error(y_test, y_pred)
|
|
logger.info("MSE: %s", mse)
|
|
classifier = LogisticRegression()
|
|
classifier.fit(X_train, y_train)
|
|
|
|
y_pred = classifier.predict(X_test)
|
|
|
|
accuracy = accuracy_score(y_test, y_pred)
|
|
logger.info("Accuracy: %s", accuracy)
|
|
y_pred_train = regressor.predict(X_train)
|
|
|
|
train_mse = mean_squared_error(y_train, y_pred_train)
|
|
logger.info("Training MSE: %s", train_mse)
|
|
|
|
train_r_squared = regressor.score(X_train, y_train)
|
|
logger.info("Training R^2: %s", train_r_squared)
|
|
|
|
test_r_squared = regressor.score(X_test, y_test)
|
|
logger.info("Testing R^2: %s", test_r_squared)
|
|
y_pred_train = classifier.predict(X_train)
|
|
|
|
train_accuracy = accuracy_score(y_train, y_pred_train)
|
|
logger.info("Training Accuracy: %s", train_accuracy)
|
|
|
|
train_f1_score = f1_score(y_train, y_pred_train, average="weighted")
|
|
logger.info("Training F1 Score: %s", train_f1_score)
|
|
|
|
test_f1_score = f1_score(y_test, y_pred, average="weighted")
|
|
logger.info("Testing F1 Score: %s", test_f1_score)
|
|
|
|
Data1 = sns.countplot(x="quality", data=wine_df)
|
|
plt.draw()
|
|
plt.waitforbuttonpress(0)
|
|
plt.close()
|
|
Data2 = sns.heatmap(wine_df.corr(), annot=True)
|
|
plt.draw()
|
|
plt.waitforbuttonpress(0)
|
|
plt.close()
|