2/23/25, 2:52 PM Model2.

ipynb - Colab

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from imblearn.over_sampling import SMOTE
from sklearn.model_selection import train_test_split, GridSearchCV
from sklearn.preprocessing import OneHotEncoder, StandardScaler
from sklearn.impute import SimpleImputer
from sklearn.ensemble import RandomForestClassifier
from xgboost import XGBClassifier
from sklearn.metrics import fbeta_score, roc_auc_score, classification_report, confusion_matrix

from google.colab import files

uploaded = files.upload()

Choose Files 2 files

test.csv(text/csv) - 152301 bytes, last modified: 2/21/2025 - 100% done
train.csv(text/csv) - 146010 bytes, last modified: 2/21/2025 - 100% done
Saving test.csv to test (1).csv
Saving train csv to train (1) csv

train_path = "/content/train.csv"
test_path = "/content/test.csv"

import os
print(os.path.exists(train_path))
print(os.path.exists(test_path))

True
True

# Load Data (for manually uploaded files in Colab or Jupyter)

train_path = "/content/train.csv"
test_path = "/content/test.csv"

if not os.path.isfile(train_path):
raise FileNotFoundError(f"Train file not found at {train_path}")
if not os.path.isfile(test_path):
raise FileNotFoundError(f"Test file not found at {test_path}")

train_df = pd.read_csv(train_path)
test_df = pd.read_csv(test_path)

# Display dataset description

print(train_df.describe(include='all'))

gender age hypertension heart_disease ever_married \

count 2555 2555.000000 2555.000000 2555.000000 2555
unique 5 NaN NaN NaN 2
top Female NaN NaN NaN Yes
freq 1309 NaN NaN NaN 1699
mean NaN 46.373777 0.099804 0.053620 NaN
std NaN 149.971251 0.299798 0.225311 NaN
min NaN 0.000100 0.000000 0.000000 NaN
25% NaN 26.000000 0.000000 0.000000 NaN
50% NaN 44.000000 0.000000 0.000000 NaN
75% NaN 60.000000 0.000000 0.000000 NaN
max NaN 7500.000000 1.000000 1.000000 NaN

work_type Residence_type avg_glucose_level bmi \

count 2555 2555 2555.000000 2454.000000
unique 5 2 NaN NaN
top Private Urban NaN NaN
https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 1/11
2/23/25, 2:52 PM Model2.ipynb - Colab
freq 1461 1288 NaN NaN
mean NaN NaN 105.534755 28.898248
std NaN NaN 44.689250 7.958036
min NaN NaN 55.220000 10.300000
25% NaN NaN 77.000000 23.500000
50% NaN NaN 91.450000 28.000000
75% NaN NaN 113.160000 33.200000
max NaN NaN 271.740000 92.000000

smoking_status stroke
count 2555 2554
unique 4 4
top never smoked 0
freq 945 2429
mean NaN NaN
std NaN NaN
min NaN NaN
25% NaN NaN
50% NaN NaN
75% NaN NaN
max NaN NaN

# Handling Missing Values

print("Missing values before handling:")
print(train_df.isnull().sum())

Missing values before handling:

gender 0
age 0
hypertension 0
heart_disease 0
ever_married 0
work_type 0
Residence_type 0
avg_glucose_level 0
bmi 101
smoking_status 0
stroke 1
dtype: int64

# Impute missing values for numerical features using median

num_features = ["age", "avg_glucose_level", "bmi"]
num_imputer = SimpleImputer(strategy="median")
train_df[num_features] = num_imputer.fit_transform(train_df[num_features])
test_df[num_features] = num_imputer.transform(test_df[num_features])

# Handling Categorical Missing Values by Filling with Most Frequent Value

cat_features = ["gender", "ever_married", "work_type", "Residence_type", "smoking_status"]
cat_imputer = SimpleImputer(strategy="most_frequent")
train_df[cat_features] = cat_imputer.fit_transform(train_df[cat_features])
test_df[cat_features] = cat_imputer.transform(test_df[cat_features])

# Double-check missing values after handling

print("Missing values after handling:")
print(train_df.isnull().sum())

Missing values after handling:

gender 0
age 0
hypertension 0
heart_disease 0
ever_married 0
work_type 0
Residence_type 0
avg_glucose_level 0

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 2/11
2/23/25, 2:52 PM Model2.ipynb - Colab
bmi 0
smoking_status 0
stroke 1
dtype: int64

# Drop row with missing stroke value

train_df = train_df.dropna(subset=["stroke"])

# Double-check missing values after handling

print("Missing values after handling:")
print(train_df.isnull().sum())

Missing values after handling:

gender 0
age 0
hypertension 0
heart_disease 0
ever_married 0
work_type 0
Residence_type 0
avg_glucose_level 0
bmi 0
smoking_status 0
stroke 0
dtype: int64

# Standardizing target variable 'stroke'

train_df["stroke"] = train_df["stroke"].replace({"Yes": 1, "yes": 1, "No": 0, "no": 0}).astype(int)

# Checking Unique Values and Their Frequencies for Target Variable

print("Stroke Unique Values Count:", train_df['stroke'].nunique())
print("Stroke Unique Values:", list(train_df['stroke'].unique()))
print("Stroke Value Counts:\n", train_df['stroke'].value_counts(), "\n")

Stroke Unique Values Count: 2

Stroke Unique Values: [0, 1]
Stroke Value Counts:
stroke
0 2429
1 125
Name: count, dtype: int64

# Checking for Negative Values

print("Checking for Negative Values:")
for feature in num_features:
negative_count = (train_df[feature] < 0).sum()
print(f"{feature}: {negative_count} negative values")

Checking for Negative Values:

age: 0 negative values
avg_glucose_level: 0 negative values
bmi: 0 negative values

# Visualizing Outliers using Boxplots

plt.figure(figsize=(12,6))
for i, feature in enumerate(num_features):
plt.subplot(1, len(num_features), i+1)
sns.boxplot(y=train_df[feature])
plt.title(f"Boxplot of {feature}")
plt.tight_layout()
plt.show()

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 3/11
2/23/25, 2:52 PM Model2.ipynb - Colab

# Visualizing Distribution of avg_glucose_level

plt.figure(figsize=(6,4))
sns.histplot(train_df['avg_glucose_level'], kde=True, bins=30)
plt.title("Distribution of avg_glucose_level")
plt.show()

# Handling Outliers using IQR method for Age Only

Q1 = train_df['age'].quantile(0.25)
Q3 = train_df['age'].quantile(0.75)
IQR = Q3 - Q1
lower_bound = Q1 - 1.5 * IQR
upper_bound = Q3 + 1.5 * IQR
train_df = train_df[(train_df['age'] >= lower_bound) & (train_df['age'] <= upper_bound)]

# Capping extreme BMI values using Winsorization (1st and 99th percentile)
bmi_lower_cap = train_df['bmi'].quantile(0.01)
https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 4/11
2/23/25, 2:52 PM Model2.ipynb - Colab
bmi_upper_cap = train_df['bmi'].quantile(0.99)
train_df['bmi'] = np.clip(train_df['bmi'], bmi_lower_cap, bmi_upper_cap)
test_df['bmi'] = np.clip(test_df['bmi'], bmi_lower_cap, bmi_upper_cap)

# Applying Log Transformation to avg_glucose_level

train_df['avg_glucose_level'] = np.log1p(train_df['avg_glucose_level']) # log1p to avoid log(0)
test_df['avg_glucose_level'] = np.log1p(test_df['avg_glucose_level'])

# Rechecking Outlier Handling with Boxplots

plt.figure(figsize=(12,6))
for i, feature in enumerate(['age', 'bmi', 'avg_glucose_level']):
plt.subplot(1, 3, i+1)
sns.boxplot(y=train_df[feature])
plt.title(f"Boxplot of {feature} After Outlier Handling")
plt.tight_layout()
plt.show()

# Checking for small or incorrect age values

print("Smallest age values:")
print(train_df[['age']].sort_values(by='age').head(10))

Smallest age values:

age
621 0.0001
1184 0.0800
2272 0.2400
113 0.2400
2006 0.3200
1467 0.3200
817 0.3200
701 0.3200
1036 0.4000
2042 0.4800

# Checking Unique Values and Their Frequencies for Each Categorical Column
for feature in cat_features:
print(f"{feature} unique values count: {train_df[feature].nunique()}")
print(f"{feature} unique values: {list(train_df[feature].unique())}")
print(f"{feature} value counts:\n{train_df[feature].value_counts()}\n")

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 5/11
2/23/25, 2:52 PM Model2.ipynb - Colab

gender unique values count: 5

gender unique values: ['Male', 'Female', 'female', 'male', 'Other']
gender value counts:
gender
Female 1308
Male 943
female 182
male 117
Other 1
Name: count, dtype: int64

ever_married unique values count: 2

ever_married unique values: ['Yes', 'No']
ever_married value counts:
ever_married
Yes 1696
No 855
Name: count, dtype: int64

work_type unique values count: 5

work_type unique values: ['Self-employed', 'Private', 'Govt_job', 'children', 'Never_worked']
work_type value counts:
work_type
Private 1458
Self-employed 412
children 341
Govt_job 330
Never_worked 10
Name: count, dtype: int64

Residence_type unique values count: 2

Residence_type unique values: ['Urban', 'Rural']
Residence_type value counts:
Residence_type
Urban 1286
Rural 1265
Name: count, dtype: int64

smoking_status unique values count: 4

smoking_status unique values: ['smokes', 'never smoked', 'Unknown', 'formerly smoked']
smoking_status value counts:
smoking_status
never smoked 944
Unknown 759
formerly smoked 452
smokes 396
Name: count, dtype: int64

# Checking Frequency of Gender Categories Before Standardization

print("Gender Distribution Before Standardization:")
print(train_df['gender'].value_counts())

Gender Distribution Before Standardization:

gender
Female 1308
Male 943
female 182
male 117
Other 1
Name: count, dtype: int64

# Standardizing Gender Values

train_df["gender"] = train_df["gender"].str.lower()
test_df["gender"] = test_df["gender"].str.lower()

# Replacing 'other' gender with the most frequent gender

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 6/11
2/23/25, 2:52 PM Model2.ipynb - Colab
most_frequent_gender = train_df["gender"].mode()[0]
train_df["gender"] = train_df["gender"].replace("other", most_frequent_gender)
test_df["gender"] = test_df["gender"].replace("other", most_frequent_gender)

# Checking Frequency of Gender Categories After Standardization

print("Gender Distribution After Standardization:")
print(train_df['gender'].value_counts())

Gender Distribution After Standardization:

gender
female 1491
male 1060
Name: count, dtype: int64

# Checking Stroke Distribution by Gender

print("Stroke Distribution by Gender:")
print(train_df.groupby('gender')['stroke'].value_counts())

Stroke Distribution by Gender:

gender stroke
female 0 1420
1 71
male 0 1007
1 53
Name: count, dtype: int64

# Checking for duplicate rows before removal

print("Duplicate rows before removal:", train_df.duplicated().sum())

Duplicate rows before removal: 0

# Checking for redundant features

print("Correlation Matrix:")

# Selecting only numeric columns for correlation

numeric_cols = train_df.select_dtypes(include=['number'])

plt.figure(figsize=(10,6))
sns.heatmap(numeric_cols.corr(), annot=True, cmap="coolwarm", fmt=".2f", linewidths=0.5)
plt.title("Feature Correlation Matrix")
plt.show()

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 7/11
2/23/25, 2:52 PM Model2.ipynb - Colab

Correlation Matrix:

scaler = StandardScaler()
scaled_train = pd.DataFrame(scaler.fit_transform(train_df[num_features]), columns=num_features)
scaled_test = pd.DataFrame(scaler.transform(test_df[num_features]), columns=num_features)

# Checking if Age and BMI are properly scaled

print("Mean and Standard Deviation after Scaling:")
print(pd.DataFrame(scaled_train, columns=['age', 'bmi']).describe().loc[['mean', 'std']])

Mean and Standard Deviation after Scaling:

age bmi
mean 2.228280e-17 -3.676662e-16
std 1.000196e+00 1.000196e+00

# Encoding Categorical Features

encoder = OneHotEncoder(drop='first', sparse_output=False)
encoded_train = pd.DataFrame(encoder.fit_transform(train_df[cat_features]), columns=encoder.get_feature_names_out(cat_
encoded_test = pd.DataFrame(encoder.transform(test_df[cat_features]), columns=encoder.get_feature_names_out(cat_featur

# Reset index to align with other features

encoded_train.reset_index(drop=True, inplace=True)
encoded_test.reset_index(drop=True, inplace=True)

# Verifying One-Hot Encoding

print("Encoded train data shape:", encoded_train.shape)
print("Encoded test data shape:", encoded_test.shape)

# Display first few rows to check encoding

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 8/11
2/23/25, 2:52 PM Model2.ipynb - Colab
print("First few rows of encoded train data:")
print(encoded_train.head())

Encoded train data shape: (2551, 10)

Encoded test data shape: (2555, 10)
First few rows of encoded train data:
gender_male ever_married_Yes work_type_Never_worked work_type_Private \
0 1.0 1.0 0.0 0.0
1 1.0 1.0 0.0 1.0
2 1.0 0.0 0.0 0.0
3 1.0 1.0 0.0 1.0
4 1.0 0.0 0.0 0.0

work_type_Self-employed work_type_children Residence_type_Urban \

0 1.0 0.0 1.0
1 0.0 0.0 0.0
2 0.0 0.0 0.0
3 0.0 0.0 1.0
4 0.0 1.0 0.0

smoking_status_formerly smoked smoking_status_never smoked \

0 0.0 0.0
1 0.0 1.0
2 0.0 1.0
3 0.0 0.0
4 1.0 0.0

smoking_status_smokes
0 1.0
1 0.0
2 0.0
3 0.0
4 0.0

# Combining Processed Features

X_train_final = pd.concat([scaled_train, encoded_train, train_df[["hypertension", "heart_disease"]].reset_index(drop=T
X_test_final = pd.concat([scaled_test, encoded_test, test_df[["hypertension", "heart_disease"]].reset_index(drop=True)

y_train_final = train_df["stroke"].astype(int)

# Train-Test Split
X_train, X_val, y_train, y_val = train_test_split(X_train_final, y_train_final, test_size=0.2, random_state=42, strati

print("Preprocessing complete.")

Preprocessing complete.

# Applying SMOTE for oversampling

smote = SMOTE(sampling_strategy=0.5, random_state=42)
X_train, y_train = smote.fit_resample(X_train, y_train)

# Train XGBoost Classifier with Hyperparameter Tuning

xgb_params = {
'n_estimators': [100, 200],
'max_depth': [3, 5, 7],
'learning_rate': [0.01, 0.05, 0.1],
'scale_pos_weight': [10, 15]
}

xgb = XGBClassifier(use_label_encoder=False, eval_metric="logloss")

grid_search_xgb = GridSearchCV(xgb, xgb_params, scoring='roc_auc', cv=3, verbose=1)
grid_search_xgb.fit(X_train, y_train)

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 9/11
2/23/25, 2:52 PM Model2.ipynb - Colab

Fitting 3 folds for each of 36 candidates, totalling 108 fits

/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:32] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:33] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:34] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:34] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:34] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:34] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:34] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:34] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:35] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:35] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:35] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:35] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 10/11
2/23/25, 2:52 PM Model2.ipynb - Colab

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:35] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:35] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:36] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:36] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:36] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:36] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:37] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:37] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:37] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:37] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:38] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:38] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:40] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:40] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:41] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:41] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:42] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

warnings.warn(smsg, UserWarning)
/usr/local/lib/python3.11/dist-packages/xgboost/core.py:158: UserWarning: [12:48:42] WARNING: /workspace/src/learn
Parameters: { "use_label_encoder" } are not used.

https://colab.research.google.com/drive/1UbZkmbbE6dt3FGmI0-hzfE9Rn7LMAa7M#scrollTo=UcGITmAB3D1r&printMode=true 11/11