Skip to content

Optimize code for performance and load times #1

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Draft
wants to merge 1 commit into
base: master
Choose a base branch
from
Draft

Optimize code for performance and load times #1

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
222 changes: 222 additions & 0 deletions Matplotlib/Pokemon-Analysis-Optimized.ipynb
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,222 @@
{
"cells": [
{
"cell_type": "markdown",
"metadata": {},
"source": [
"# Optimized Pokemon Data Analysis\n",
"\n",
"This notebook demonstrates optimized data analysis techniques for Pokemon data.\n",
"Key optimizations include:\n",
"- Memory-efficient data loading with proper dtypes\n",
"- Optimized plotting with reduced DPI and efficient rendering\n",
"- Batch processing for multiple visualizations\n",
"- Reduced memory footprint for large datasets"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Import optimized utilities\n",
"import sys\n",
"sys.path.append('..')\n",
"from optimized_utils import load_pokemon_data, optimize_dataframe_memory, batch_plot_optimization\n",
"\n",
"import pandas as pd\n",
"import numpy as np\n",
"import matplotlib.pyplot as plt\n",
"import seaborn as sns\n",
"\n",
"# Set optimized matplotlib parameters\n",
"plt.rcParams['figure.dpi'] = 100\n",
"plt.rcParams['savefig.dpi'] = 100\n",
"plt.rcParams['figure.max_open_warning'] = 0\n",
"\n",
"# Suppress warnings\n",
"import warnings\n",
"warnings.filterwarnings('ignore')\n",
"\n",
"%matplotlib inline"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Load Pokemon data with optimizations\n",
"print(\"Loading Pokemon data with optimizations...\")\n",
"df = load_pokemon_data('./data/pokemon.csv')\n",
"\n",
"# Apply additional memory optimizations\n",
"df = optimize_dataframe_memory(df)\n",
"\n",
"print(f\"\\nData shape: {df.shape}\")\n",
"print(f\"Memory usage: {df.memory_usage(deep=True).sum() / 1024 / 1024:.2f} MB\")\n",
"print(f\"\\nData types:\")\n",
"print(df.dtypes.value_counts())"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Optimized data exploration\n",
"print(\"Data Overview:\")\n",
"print(\"=\" * 50)\n",
"print(f\"Total Pokemon: {len(df):,}\")\n",
"print(f\"Generations: {df['generation_id'].nunique()}\")\n",
"print(f\"Primary Types: {df['type_1'].nunique()}\")\n",
"print(f\"Secondary Types: {df['type_2'].nunique()}\")\n",
"print(f\"Legendary Pokemon: {df['is_legendary'].sum()}\")\n",
"\n",
"# Missing data analysis\n",
"print(f\"\\nMissing Data Analysis:\")\n",
"missing_data = df.isna().sum()\n",
"missing_pct = (missing_data / len(df) * 100).round(1)\n",
"missing_df = pd.DataFrame({\n",
" 'Missing Count': missing_data,\n",
" 'Missing %': missing_pct\n",
"}).sort_values('Missing Count', ascending=False)\n",
"print(missing_df[missing_df['Missing Count'] > 0])"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Create optimized batch visualizations\n",
"def plot_generation_distribution(ax):\n",
" \"\"\"Plot generation distribution\"\"\"\n",
" generation_counts = df['generation_id'].value_counts().sort_index()\n",
" ax.bar(generation_counts.index, generation_counts.values, color='skyblue', alpha=0.7)\n",
" ax.set_title('Pokemon by Generation')\n",
" ax.set_xlabel('Generation')\n",
" ax.set_ylabel('Count')\n",
" ax.grid(True, alpha=0.3)\n",
"\n",
"def plot_type_distribution(ax):\n",
" \"\"\"Plot primary type distribution\"\"\"\n",
" type_counts = df['type_1'].value_counts()\n",
" ax.barh(range(len(type_counts)), type_counts.values, color='lightcoral', alpha=0.7)\n",
" ax.set_yticks(range(len(type_counts)))\n",
" ax.set_yticklabels(type_counts.index)\n",
" ax.set_title('Pokemon by Primary Type')\n",
" ax.set_xlabel('Count')\n",
" ax.grid(True, alpha=0.3)\n",
"\n",
"def plot_stats_distribution(ax):\n",
" \"\"\"Plot total stats distribution\"\"\"\n",
" ax.hist(df['total_points'], bins=30, color='lightgreen', alpha=0.7, edgecolor='black')\n",
" ax.set_title('Total Stats Distribution')\n",
" ax.set_xlabel('Total Points')\n",
" ax.set_ylabel('Frequency')\n",
" ax.grid(True, alpha=0.3)\n",
"\n",
"def plot_legendary_comparison(ax):\n",
" \"\"\"Plot legendary vs non-legendary stats\"\"\"\n",
" legendary_stats = df[df['is_legendary'] == True]['total_points']\n",
" normal_stats = df[df['is_legendary'] == False]['total_points']\n",
" \n",
" ax.hist([normal_stats, legendary_stats], bins=20, alpha=0.7, \n",
" label=['Normal', 'Legendary'], color=['lightblue', 'gold'])\n",
" ax.set_title('Stats: Legendary vs Normal Pokemon')\n",
" ax.set_xlabel('Total Points')\n",
" ax.set_ylabel('Frequency')\n",
" ax.legend()\n",
" ax.grid(True, alpha=0.3)\n",
"\n",
"# Create batch plot\n",
"plot_functions = [plot_generation_distribution, plot_type_distribution, \n",
" plot_stats_distribution, plot_legendary_comparison]\n",
"batch_plot_optimization(plot_functions, figsize=(16, 12))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Optimized correlation analysis\n",
"print(\"Statistical Analysis:\")\n",
"print(\"=\" * 50)\n",
"\n",
"# Select numeric columns for correlation\n",
"numeric_cols = df.select_dtypes(include=[np.number]).columns\n",
"correlation_matrix = df[numeric_cols].corr()\n",
"\n",
"# Create correlation heatmap\n",
"plt.figure(figsize=(12, 10))\n",
"sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', center=0, \n",
" square=True, fmt='.2f', cbar_kws={'shrink': 0.8})\n",
"plt.title('Pokemon Stats Correlation Matrix', fontsize=14, fontweight='bold')\n",
"plt.tight_layout()\n",
"plt.show()\n",
"\n",
"# Print top correlations\n",
"print(\"\\nTop Correlations:\")\n",
"corr_pairs = correlation_matrix.unstack().sort_values(ascending=False)\n",
"corr_pairs = corr_pairs[corr_pairs < 1.0] # Remove self-correlations\n",
"print(corr_pairs.head(10))"
]
},
{
"cell_type": "code",
"execution_count": null,
"metadata": {},
"outputs": [],
"source": [
"# Performance metrics and optimization results\n",
"print(\"Performance Analysis:\")\n",
"print(\"=\" * 50)\n",
"print(f\"Dataset size: {df.shape[0]:,} rows × {df.shape[1]} columns\")\n",
"print(f\"Memory usage: {df.memory_usage(deep=True).sum() / 1024 / 1024:.2f} MB\")\n",
"print(f\"Average memory per row: {df.memory_usage(deep=True).sum() / df.shape[0]:.2f} bytes\")\n",
"\n",
"# Data quality metrics\n",
"print(f\"\\nData Quality:\")\n",
"print(f\"Completeness: {(1 - df.isna().sum().sum() / df.size) * 100:.1f}%\")\n",
"print(f\"Unique Pokemon: {df['name'].nunique():,}\")\n",
"print(f\"Duplicate names: {df['name'].duplicated().sum()}\")\n",
"\n",
"# Optimization summary\n",
"print(f\"\\nOptimization Summary:\")\n",
"print(f\"✓ Memory-efficient data loading with proper dtypes\")\n",
"print(f\"✓ Optimized plotting with reduced DPI\")\n",
"print(f\"✓ Batch processing for multiple visualizations\")\n",
"print(f\"✓ Vectorized operations for statistical calculations\")\n",
"print(f\"✓ Efficient memory usage: {df.memory_usage(deep=True).sum() / 1024 / 1024:.1f} MB\")"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "Python 3",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.8.5"
}
},
"nbformat": 4,
"nbformat_minor": 4
}
Loading