# Importing necessary libraries
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
!pip install -q yfinance

# Importing data using Yahoo Finance API
import yfinance as yf

# Downloading historical data for AT&T (a major telecom company)
data = yf.download('T', start='2020-01-01', end='2023-01-01')
data.head()

# Plotting the distribution of stock prices (Close and Adj Close)
plt.figure(figsize=(12, 6))
sns.histplot(data[['Close', 'Adj Close']], kde=True, element='step')
plt.title('Distribution of Stock Prices')
plt.xlabel('Stock Price')
plt.ylabel('Frequency')
plt.legend(['Close', 'Adj Close'])
plt.show()

# Calculating 7-day and 30-day moving averages for the 'Close' price
data['7_day_MA_Close'] = data['Close'].rolling(window=7).mean()
data['30_day_MA_Close'] = data['Close'].rolling(window=30).mean()

# Calculating 7-day and 30-day moving averages for the 'Volume'
data['7_day_MA_Volume'] = data['Volume'].rolling(window=7).mean()
data['30_day_MA_Volume'] = data['Volume'].rolling(window=30).mean()

# Displaying the first few rows of the modified dataset
data.head()

# Importing KMeans from sklearn
from sklearn.cluster import KMeans

# Dropping rows with NaN values
data_clustering = data.dropna()

# Selecting features for clustering
features = ['7_day_MA_Close', '30_day_MA_Close', '7_day_MA_Volume', '30_day_MA_Volume']
X = data_clustering[features]

# Fitting KMeans model
kmeans = KMeans(n_clusters=3, random_state=0).fit(X)

# Adding cluster labels to the original data
data_clustering['Cluster'] = kmeans.labels_

# Displaying the first few rows of data with cluster labels
data_clustering.head()

# Grouping the data by cluster and calculating the mean for each feature
cluster_summary = data_clustering.groupby('Cluster').mean()

# Displaying the statistical summary of each cluster
cluster_summary

# Creating a dashboard to visualize cluster insights
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# Plotting the average Adjusted Close Price for each cluster
sns.barplot(x=cluster_summary.index, y='Adj Close', data=cluster_summary, ax=axes[0, 0])
axes[0, 0].set_title('Average Adjusted Close Price by Cluster')

# Plotting the average Volume for each cluster
sns.barplot(x=cluster_summary.index, y='Volume', data=cluster_summary, ax=axes[0, 1])
axes[0, 1].set_title('Average Volume by Cluster')

# Plotting the average 7-day MA Close for each cluster
sns.barplot(x=cluster_summary.index, y='7_day_MA_Close', data=cluster_summary, ax=axes[1, 0])
axes[1, 0].set_title('Average 7-day MA Close by Cluster')

# Plotting the average 30-day MA Close for each cluster
sns.barplot(x=cluster_summary.index, y='30_day_MA_Close', data=cluster_summary, ax=axes[1, 1])
axes[1, 1].set_title('Average 30-day MA Close by Cluster')

plt.tight_layout()
plt.show()

# Renaming cluster labels for better interpretation
cluster_names = {
    0: 'Stable Segment',
    1: 'Active/Premium Segment',
    2: 'Volatile/Riskier Segment'
}
cluster_summary.rename(index=cluster_names, inplace=True)

# Creating a dashboard with renamed cluster labels
fig, axes = plt.subplots(2, 2, figsize=(14, 10))

# Plotting the average Adjusted Close Price for each cluster
sns.barplot(x=cluster_summary.index, y='Adj Close', data=cluster_summary, ax=axes[0, 0])
axes[0, 0].set_title('Average Adjusted Close Price by Cluster')

# Plotting the average Volume for each cluster
sns.barplot(x=cluster_summary.index, y='Volume', data=cluster_summary, ax=axes[0, 1])
axes[0, 1].set_title('Average Volume by Cluster')

# Plotting the average 7-day MA Close for each cluster
sns.barplot(x=cluster_summary.index, y='7_day_MA_Close', data=cluster_summary, ax=axes[1, 0])
axes[1, 0].set_title('Average 7-day MA Close by Cluster')

# Plotting the average 30-day MA Close for each cluster
sns.barplot(x=cluster_summary.index, y='30_day_MA_Close', data=cluster_summary, ax=axes[1, 1])
axes[1, 1].set_title('Average 30-day MA Close by Cluster')

plt.tight_layout()
plt.show()

from math import pi

# Function to create radar chart
def create_radar_chart(data, title):
    labels = data.index
    num_vars = len(labels)

    angles = np.linspace(0, 2 * np.pi, num_vars, endpoint=False).tolist()
    angles += angles[:1]

    fig, ax = plt.subplots(figsize=(6, 6), subplot_kw=dict(polar=True))
    ax.fill(angles, data.tolist() + data.tolist()[:1], color='blue', alpha=0.25)
    ax.set_yticklabels([])
    ax.set_xticks(angles[:-1])
    ax.set_xticklabels(labels)

    ax.set_title(title, size=14, color='blue', y=1.1)
    plt.show()

# Normalizing the data for radar chart
cluster_summary_normalized = (cluster_summary - cluster_summary.min()) / (cluster_summary.max() - cluster_summary.min())

# Creating radar charts for each cluster
for cluster, row in cluster_summary_normalized.iterrows():
    create_radar_chart(row, f'Radar Chart for {cluster}')