Chapter 1: The Policy Landscape of Materials Science

# Install the required libraries
pip install matplotlib pandas wordcloud

"""
Example: Keyword Extraction and Visualization from Policy Documents

Purpose: Extract important keywords from a materials science policy document
Level: Beginner
Runtime: ~10 sec
Dependencies: matplotlib, wordcloud
"""

import re
from collections import Counter
import matplotlib.pyplot as plt
from wordcloud import WordCloud

# Sample policy document (in practice, obtained from government materials)
policy_text = """
The Materials Innovation Strengthening Strategy aims to strengthen the
international competitiveness of our nation's materials science and technology
and to contribute to realizing a sustainable society. By integrating
data-driven materials development, materials informatics, computational science,
and experimental techniques, it accelerates the shortening of materials
development periods and the creation of high-performance materials. It also
promotes industry-academia-government collaboration and strengthens the
formation of open innovation hubs, human resource development, and
international cooperation. Priority fields include rechargeable battery
materials, carbon fiber composites, semiconductor materials, biomaterials,
and quantum materials.
"""

# Simple English stopword list (common words carry little meaning as keywords)
stopwords = {'the', 'and', 'of', 'to', 'in', 'it', 'by', 'our', 'as', 'for',
             'also', 'that', 'with', 'these', 'this', 'are', 'is', 'be',
             'from', 'on', 'at', 'or', 'an'}

# Tokenize into words (keywords are typically multi-letter content words)
words = re.findall(r'[a-z][a-z-]+', policy_text.lower())
words = [w for w in words if len(w) > 3 and w not in stopwords]

# Count frequent words
word_counts = Counter(words)
top_words = word_counts.most_common(15)

# Visualization
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 6))

# Bar chart
word_labels, counts = zip(*top_words)
ax1.barh(word_labels, counts, color='#f093fb')
ax1.set_xlabel('Frequency', fontsize=12)
ax1.set_title('Key Terms in the Policy Document (Top 15)', fontsize=14, fontweight='bold')
ax1.invert_yaxis()

# Word cloud
wordcloud = WordCloud(
    width=800,
    height=600,
    background_color='white',
    colormap='Purples'
).generate(' '.join(words))

ax2.imshow(wordcloud, interpolation='bilinear')
ax2.axis('off')
ax2.set_title('Word Cloud', fontsize=14, fontweight='bold')

plt.tight_layout()
plt.savefig('policy_keywords.png', dpi=300, bbox_inches='tight')
plt.show()

print("Keyword extraction complete!")
print(f"\nTop 5 key terms:")
for word, count in top_words[:5]:
    print(f"  {word}: {count} times")

"""
Example: Comparison of Materials Science R&D Investment by Country

Purpose: Visualize the R&D investment trends of major countries
Level: Beginner
Runtime: ~5 sec
Dependencies: matplotlib, pandas
"""

import pandas as pd
import matplotlib.pyplot as plt

# Sample data (in practice obtained from the OECD Science, Technology and Innovation Scoreboard, etc.)
data = {
    'Year': [2015, 2016, 2017, 2018, 2019, 2020, 2021, 2022],
    'Japan': [2.5, 2.6, 2.7, 2.8, 2.9, 3.0, 3.2, 3.4],  # Unit: billion USD
    'USA': [8.5, 9.0, 9.5, 10.0, 10.5, 11.0, 11.8, 12.5],
    'EU': [6.0, 6.2, 6.5, 6.8, 7.0, 7.3, 7.8, 8.2],
    'China': [5.0, 6.5, 8.0, 9.5, 11.0, 12.5, 14.0, 15.5],
    'Korea': [1.2, 1.3, 1.4, 1.5, 1.6, 1.7, 1.9, 2.1]
}

df = pd.DataFrame(data)

# Visualization
fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(14, 6))

# Trend graph
for country in ['Japan', 'USA', 'EU', 'China', 'Korea']:
    ax1.plot(df['Year'], df[country], marker='o', linewidth=2, label=country)

ax1.set_xlabel('Year', fontsize=12)
ax1.set_ylabel('R&D Investment (billion USD)', fontsize=12)
ax1.set_title('Trends in Materials Science R&D Investment by Major Countries', fontsize=14, fontweight='bold')
ax1.legend()
ax1.grid(True, alpha=0.3)

# Investment comparison for 2022 (bar chart)
latest_year = df[df['Year'] == 2022].iloc[0]
countries = ['Japan', 'USA', 'EU', 'China', 'Korea']
investments = [latest_year[c] for c in countries]

colors = ['#f093fb', '#4285f4', '#34a853', '#ea4335', '#fbbc04']
ax2.bar(countries, investments, color=colors)
ax2.set_ylabel('R&D Investment (billion USD)', fontsize=12)
ax2.set_title('R&D Investment by Country in 2022', fontsize=14, fontweight='bold')
ax2.grid(True, alpha=0.3, axis='y')

plt.tight_layout()
plt.savefig('research_investment_comparison.png', dpi=300, bbox_inches='tight')
plt.show()

print("📊 Analysis results:")
print(f"Investment growth rate from 2015 to 2022:")
for country in countries:
    growth = ((df[country].iloc[-1] / df[country].iloc[0]) - 1) * 100
    print(f"  {country}: {growth:.1f}%")

"""
Example: Time-Series Changes in Policy Priority Fields

Purpose: Track the evolution of priority keywords in policy documents
Level: Intermediate
Runtime: ~10 sec
Dependencies: pandas, matplotlib
"""

import pandas as pd
import matplotlib.pyplot as plt

# Sample data: number of mentions of priority fields in policy documents each year
data = {
    'Year': [2015, 2017, 2019, 2021, 2023],
    'Nanomaterials': [45, 40, 35, 30, 25],
    'Composite Materials': [30, 35, 40, 42, 45],
    'Battery Materials': [20, 30, 45, 60, 75],
    'Biomaterials': [15, 20, 25, 35, 40],
    'Carbon-Neutral Materials': [5, 10, 25, 50, 70],
    'Materials Informatics': [10, 20, 35, 55, 65]
}

df = pd.DataFrame(data)

# Visualization: stacked area chart
fig, ax = plt.subplots(figsize=(12, 7))

fields = ['Nanomaterials', 'Composite Materials', 'Battery Materials', 'Biomaterials',
          'Carbon-Neutral Materials', 'Materials Informatics']
colors = ['#e3f2fd', '#bbdefb', '#90caf9', '#64b5f6', '#42a5f5', '#2196f3']

ax.stackplot(df['Year'],
             [df[field] for field in fields],
             labels=fields,
             colors=colors,
             alpha=0.8)

ax.set_xlabel('Year', fontsize=12)
ax.set_ylabel('Number of Mentions in Policy Documents', fontsize=12)
ax.set_title('Evolution of Priority Fields in Materials Science Policy (2015-2023)', fontsize=14, fontweight='bold')
ax.legend(loc='upper left', fontsize=10)
ax.grid(True, alpha=0.3, axis='y')

plt.tight_layout()
plt.savefig('policy_trend_analysis.png', dpi=300, bbox_inches='tight')
plt.show()

print("🔍 Trend analysis:")
print("\nRapidly growing fields:")
for field in fields:
    growth = df[field].iloc[-1] - df[field].iloc[0]
    if growth > 40:
        print(f"  ✨ {field}: +{growth} mentions ({df[field].iloc[0]}→{df[field].iloc[-1]})")

print("\nDeclining fields:")
for field in fields:
    growth = df[field].iloc[-1] - df[field].iloc[0]
    if growth < 0:
        print(f"  ⚠️ {field}: {growth} mentions ({df[field].iloc[0]}→{df[field].iloc[-1]})")

"""
Example: Simulation and Analysis of a Policy Database

Purpose: Filtering and statistical analysis of policy data
Level: Intermediate
Runtime: ~5 sec
Dependencies: pandas
"""

import pandas as pd
import numpy as np

# Virtual policy database (in practice obtained from an API, etc.)
np.random.seed(42)
policies = []

countries = ['Japan', 'USA', 'EU', 'China', 'Korea']
categories = ['Research Funding', 'Human Resource Development', 'Industry-Academia Collaboration', 'International Cooperation', 'Standardization']
years = range(2015, 2024)

for _ in range(100):
    policies.append({
        'Country': np.random.choice(countries),
        'Category': np.random.choice(categories),
        'Year': np.random.choice(years),
        'Budget_Million_USD': np.random.randint(10, 500),
        'Num_Institutions': np.random.randint(5, 50)
    })

df = pd.DataFrame(policies)

# Analysis 1: Number of policies by country and category
policy_count = df.groupby(['Country', 'Category']).size().unstack(fill_value=0)

print("=" * 60)
print("Number of Policies by Country and Category")
print("=" * 60)
print(policy_count)

# Analysis 2: Budget statistics
print("\n" + "=" * 60)
print("Average Budget by Country (Million USD)")
print("=" * 60)
budget_stats = df.groupby('Country')['Budget_Million_USD'].agg(['mean', 'sum', 'count'])
budget_stats.columns = ['Mean', 'Total', 'Policy Count']
print(budget_stats.round(1))

# Analysis 3: Trend analysis
print("\n" + "=" * 60)
print("Number of Policies by Year")
print("=" * 60)
yearly_trend = df.groupby('Year').size()
print(yearly_trend)

# Analysis 4: Extracting the top policies
print("\n" + "=" * 60)
print("Top 5 Policies by Budget")
print("=" * 60)
top_policies = df.nlargest(5, 'Budget_Million_USD')[['Country', 'Category', 'Year', 'Budget_Million_USD']]
print(top_policies.to_string(index=False))

# Visualization (budget comparison by country)
import matplotlib.pyplot as plt

fig, ax = plt.subplots(figsize=(10, 6))
budget_by_country = df.groupby('Country')['Budget_Million_USD'].sum().sort_values(ascending=False)
budget_by_country.plot(kind='bar', ax=ax, color='#f093fb')
ax.set_ylabel('Total Budget (Million USD)', fontsize=12)
ax.set_title('Total Policy Budget by Country (2015-2023)', fontsize=14, fontweight='bold')
ax.set_xlabel('Country', fontsize=12)
plt.xticks(rotation=0)
plt.grid(True, alpha=0.3, axis='y')
plt.tight_layout()
plt.savefig('budget_by_country.png', dpi=300, bbox_inches='tight')
plt.show()

print("\n✅ Analysis complete! Please check the graph.")