Project 2

import pandas as pd

import numpy as np

import matplotlib.pyplot as plt

from sklearn.preprocessing import StandardScaler

from sklearn.decomposition import PCA

from sklearn.cluster import KMeans

from scipy.cluster.hierarchy import dendrogram, linkage

# Load the data from the CSV file

file_path = 'path_to_your_directory/country_data.csv'

df = pd.read_csv(file_path)

# Select relevant columns for analysis

columns_for_analysis = ['child_mort', 'exports', 'health', 'imports', 'income', 'inflation', 'life_expec', 'total_fer', 'gdpp']

data_for_analysis = df[columns_for_analysis]

# 1. Data Preprocessing: Standardize the data

scaler = StandardScaler()

scaled_data = scaler.fit_transform(data_for_analysis)

# 2. Principal Component Analysis (PCA):

n_components = 2

pca = PCA(n_components=n_components)

pca_result = pca.fit_transform(scaled_data)

# Plot the explained variance

explained_variance_ratio = pca.explained_variance_ratio_

cumulative_explained_variance = np.cumsum(explained_variance_ratio)

plt.plot(range(1, n_components + 1), cumulative_explained_variance, marker='o', linestyle='--')

plt.title('Cumulative Explained Variance')

plt.xlabel('Number of Principal Components')

plt.ylabel('Cumulative Explained Variance')

plt.show()

# 3. K-Means Clustering:

n_clusters = 3

kmeans = KMeans(n_clusters=n_clusters, random_state=42)

cluster_labels = kmeans.fit_predict(pca_result)

# Visualize K-Means Clustering results

df['cluster_kmeans'] = cluster_labels

plt.scatter(pca_result[:, 0], pca_result[:, 1], c=cluster_labels, cmap='viridis', alpha=0.8)

plt.title('K-Means Clustering Results')

plt.xlabel('Principal Component 1')

plt.ylabel('Principal Component 2')

plt.show()

# 4. Hierarchical Clustering:

linked = linkage(scaled_data, 'ward')

# Plot the dendrogram

dendrogram(linked, orientation='top', distance_sort='descending', show_leaf_counts=True)

plt.title('Hierarchical Clustering Dendrogram')

plt.xlabel('Countries')

plt.ylabel('Distance')

plt.show()

 # 5. Interpretation and Recommendation:

# Analyze the clusters and dendrogram to suggest countries in need of aid based on the analysis.

# You can check the cluster centroids for K-Means or the dendrogram for hierarchical clustering.

# Example of getting cluster centroids for K-Means

cluster_centroids = pd.DataFrame(kmeans.cluster_centers_, columns=['PC1', 'PC2'])

print(cluster_centroids)

# Example of getting countries in each cluster

clustered_data = pd.concat([df['country'], df['cluster_kmeans']], axis=1)

# Assuming 'cluster_kmeans' is the cluster column created during K-Means

countries_in_cluster_0 = clustered_data[clustered_data['cluster_kmeans'] == 0]['country'].tolist()

countries_in_cluster_1 = clustered_data[clustered_data['cluster_kmeans'] == 1]['country'].tolist()

countries_in_cluster_2 = clustered_data[clustered_data['cluster_kmeans'] == 2]['country'].tolist()

print("Countries in Cluster 0:", countries_in_cluster_0)

print("Countries in Cluster 1:", countries_in_cluster_1)

print("Countries in Cluster 2:", countries_in_cluster_2)