# UTS - PENGANTAR DATA SAINS
# Nama: [Nama Lengkap]
# NIM: [NIM]
# Judul Analisis: [Judul Proyek]

"""
## 📊 ANALISIS [JUDUL DATASET]
### Executive Summary
[Ringkasan 3-5 kalimat tentang proyek dan temuan utama]
"""

# ========================================
# 1. SETUP & IMPORT LIBRARIES
# ========================================
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
import warnings
warnings.filterwarnings('ignore')

# Setup visualization style
plt.style.use('seaborn-v0_8')
sns.set_palette("husl")
print("✅ Libraries imported successfully")

# ========================================
# 2. DATA COLLECTION
# ========================================
"""
### 📥 Dataset Information
- **Source**: [URL atau nama sumber]
- **Description**: [Deskripsi dataset]
- **Size**: [Jumlah rows x columns]
- **Period**: [Jika ada timeframe]
"""

# Load data
df = pd.read_csv('your_dataset.csv')
print(f"Dataset shape: {df.shape}")
print(f"Columns: {list(df.columns)}")

# Display first few rows
df.head()

# ========================================
# 3. DATA EXPLORATION
# ========================================
"""
### 🔍 Initial Data Exploration
"""

# Data types
print("Data Types:")
print(df.dtypes)

# Basic statistics
print("\nStatistical Summary:")
df.describe()

# Missing values
print("\nMissing Values:")
df.isnull().sum()

# Unique values
for col in df.select_dtypes(include='object').columns:
    print(f"\n{col}: {df[col].nunique()} unique values")
    if df[col].nunique() < 10:
        print(df[col].value_counts())

# ========================================
# 4. DATA CLEANING
# ========================================
"""
### 🧹 Data Cleaning Process
"""

# Document original shape
original_shape = df.shape
print(f"Original shape: {original_shape}")

# 1. Handle missing values
# [Strategy explanation]
df_clean = df.copy()

# Example: Fill numeric with median
numeric_cols = df_clean.select_dtypes(include=[np.number]).columns
for col in numeric_cols:
    if df_clean[col].isnull().sum() > 0:
        df_clean[col].fillna(df_clean[col].median(), inplace=True)
        print(f"Filled {col} with median")

# 2. Remove duplicates
duplicates = df_clean.duplicated().sum()
if duplicates > 0:
    df_clean = df_clean.drop_duplicates()
    print(f"Removed {duplicates} duplicate rows")

# 3. Fix data types
# [Convert as needed]

# Final shape
print(f"\nFinal shape after cleaning: {df_clean.shape}")
print(f"Rows removed: {original_shape[0] - df_clean.shape[0]}")

# ========================================
# 5. FEATURE ENGINEERING
# ========================================
"""
### 🔧 Feature Engineering
"""

# Create new meaningful features
# Example:
# df_clean['new_feature'] = df_clean['col1'] / df_clean['col2']

# ========================================
# 6. STATISTICAL ANALYSIS
# ========================================
"""
### 📊 Statistical Analysis
"""

# Correlation matrix
correlation_matrix = df_clean.select_dtypes(include=[np.number]).corr()

# Distribution analysis
# [Analyze key variables]

# Outlier detection
Q1 = df_clean.quantile(0.25)
Q3 = df_clean.quantile(0.75)
IQR = Q3 - Q1

# ========================================
# 7. DATA VISUALIZATION
# ========================================
"""
### 📈 Data Visualization
"""

# Create figure with subplots
fig = plt.figure(figsize=(20, 15))
fig.suptitle('Data Analysis Dashboard', fontsize=20, fontweight='bold')

# Visualization 1: Distribution
ax1 = plt.subplot(3, 3, 1)
# [Your code here]
ax1.set_title('Distribution of [Variable]')

# Visualization 2: Correlation Heatmap
ax2 = plt.subplot(3, 3, 2)
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', center=0)
ax2.set_title('Correlation Matrix')

# Visualization 3: Time Series (if applicable)
ax3 = plt.subplot(3, 3, 3)
# [Your code here]

# Visualization 4: Bar Chart
ax4 = plt.subplot(3, 3, 4)
# [Your code here]

# Visualization 5: Scatter Plot
ax5 = plt.subplot(3, 3, 5)
# [Your code here]

# Add more visualizations...

plt.tight_layout()
plt.show()

# ========================================
# 8. KEY INSIGHTS
# ========================================
"""
### 💡 Key Insights

1. **Finding 1**: [Description and interpretation]
2. **Finding 2**: [Description and interpretation]
3. **Finding 3**: [Description and interpretation]
4. **Finding 4**: [Description and interpretation]
5. **Finding 5**: [Description and interpretation]
"""

# ========================================
# 9. CONCLUSIONS & RECOMMENDATIONS
# ========================================
"""
### 📌 Conclusions

[Summary of main findings]

### 🎯 Recommendations

1. **Business Recommendation 1**: [Actionable insight]
2. **Business Recommendation 2**: [Actionable insight]
3. **Business Recommendation 3**: [Actionable insight]

### 🔮 Future Work

- [Suggestion for further analysis]
- [Additional data that could be useful]
- [Advanced techniques to apply]
"""

# ========================================
# 10. REFERENCES
# ========================================
"""
### 📚 References

- Dataset Source: [URL]
- Documentation: [Any references used]
- Additional Resources: [If any]
"""