python_analysis/second_semestr/pract5-2.py - main - Nik_voz/rgpu_python_analysis

python_analysis/second_semestr/pract5-2.py

80 строк2 KB

Nick-voz

feat: add decision tree classifier and random forest regressor implementations

26 мар 2026, 06:50

26 мар 2026, 06:50c1feb41

import os

import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from dotenv import load_dotenv
from sklearn.metrics import accuracy_score
from sklearn.tree import DecisionTreeClassifier
from sklearn.tree import plot_tree

load_dotenv()

TRAIN_PATH = os.getenv("TRAIN_PATH") or "train.csv"
TEST_PATH = os.getenv("TEST_PATH") or "test.csv"

train_data = pd.read_csv(TRAIN_PATH)
test_data = pd.read_csv(TEST_PATH)


plt.figure(figsize=(15, 10))

plt.subplot(2, 3, 1)
sns.countplot(x="Survived", data=train_data)
plt.title("Выжившие/Погибшие")

plt.subplot(2, 3, 2)
sns.countplot(x="Survived", hue="Sex", data=train_data)
plt.title("Выживаемость по полу")

plt.subplot(2, 3, 3)
sns.countplot(x="Survived", hue="Pclass", data=train_data)
plt.title("Выживаемость по классу")

plt.subplot(2, 3, 4)
sns.countplot(x="Survived", hue="SibSp", data=train_data)
plt.title("Выживаемость по количеству братьев/сестер/супругов")

plt.subplot(2, 3, 5)
sns.countplot(x="Survived", hue="Parch", data=train_data)
plt.title("Выживаемость по количеству родителей/детей")

plt.tight_layout()
plt.savefig("titanic_stats.png", dpi=300, bbox_inches="tight")

features = ["Sex", "Pclass", "SibSp", "Parch"]

y = train_data["Survived"]

X = pd.get_dummies(train_data[features])
X_test = pd.get_dummies(test_data[features])

model = DecisionTreeClassifier(
    max_depth=5,
    random_state=1,
)

model.fit(X, y)
train_predictions = model.predict(X)
train_accuracy = accuracy_score(y, train_predictions)


plt.figure(figsize=(20, 15))
plot_tree(
    model,
    feature_names=list(X.columns),
    class_names=["Погиб", "Выжил"],
    filled=True,
    rounded=True,
)
plt.title("Дерево решений (Titanic)")
plt.savefig("titanic_tree.png", dpi=300, bbox_inches="tight")

feature_importance = pd.DataFrame(
    {"feature": X.columns, "importance": model.feature_importances_}
).sort_values("importance", ascending=False)

plt.figure(figsize=(15, 10))
sns.barplot(data=feature_importance, x="importance", y="feature")
plt.title("Важность признаков")
plt.savefig("titanic_importance_of_features.png", dpi=300, bbox_inches="tight")