edas

import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sns

from sklearn.preprocessing import LabelEncoder, StandardScaler
from sklearn.model_selection import train_test_split
from sklearn.linear_model import LinearRegression, LogisticRegression
from sklearn.tree import DecisionTreeClassifier, plot_tree
from sklearn.naive_bayes import GaussianNB
from sklearn.ensemble import RandomForestClassifier, AdaBoostClassifier, GradientBoostingClassifier
from sklearn.neural_network import MLPClassifier
from sklearn.cluster import KMeans
from sklearn.metrics import mean_absolute_error, mean_squared_error, accuracy_score, classification_report, confusion_matrix, r2_score
from sklearn.decomposition import PCA

import warnings
warnings.filterwarnings("ignore")

df = pd.read_csv(r"D:\Nithilan\SEM 4\PRML\Datasets\CVD_cleaned.csv")
df.head()

df.info()

df.shape

df.describe()

df.isnull().sum()

num_col = df.select_dtypes(include = "number")
for i in num_col:
    df[i] = df[i].fillna(df[i].median())
    
for i in num_col:
    plt.boxplot(df[i])
    plt.title(i)
    plt.show()

for i in num_col:
    sns.histplot(df[i], kde = True, bins = 20)
    plt.show()

le = LabelEncoder()
obj_col = df.select_dtypes(include = "object")
df_enc = df.copy()
for i in obj_col.columns:
    df_enc[i] = le.fit_transform(df_enc[i])

corr = df_enc.corr()
plt.figure(figsize=(10, 12))
sns.heatmap(corr, annot = True, cmap = "coolwarm", fmt = ".2f")
plt.show()
target_corr = corr["Heart_Disease"].sort_values(ascending = False)
print(target_corr)