from google.cloud import bigquery
client = bigquery.Client(project='fred-employment-initial-test')

# Your query string
query = """
SELECT *
FROM `fred-employment-initial-test.fred_data.fred_data_withnotes`
WHERE series_id IN ('PAYEMS', 'GDP')
"""

# Run the query
query_job = client.query(query)

# Convert the query results to a pandas DataFrame
data = query_job.to_dataframe()

# Display the first few rows
print(data.head())

import pandas_datareader.data as web

# Define the start and end dates
start = '1947-01-01'  # Start date (you can adjust this)
end = '2024-12-31'    # End date (you can adjust this)

# Fetch GDP data
gdp_data = web.DataReader('GDP', 'fred', start, end)
print(gdp_data.head())

# Remove timezone information from the date columns in both DataFrames
payroll_data['date'] = pd.to_datetime(payroll_data['date']).dt.tz_localize(None)
gdp_data['date'] = pd.to_datetime(gdp_data['date']).dt.tz_localize(None)

# Now merge the DataFrames
merged_data = pd.merge(payroll_data[['date', 'PAYEMS']], gdp_data, on='date')
print(merged_data.head())

!pip install mplcyberpunk

import matplotlib.pyplot as plt
import mplcyberpunk
import pandas as pd

# Use the Cyberpunk style
plt.style.use("cyberpunk")

# Create the figure and axis
fig, ax1 = plt.subplots(figsize=(14, 7))

# Plot the Nonfarm Payroll Employment (PAYEMS) on the first axis
ax1.plot(merged_data['date'], merged_data['PAYEMS'], color='#ff1493', label='Nonfarm Payroll Employment (PAYEMS)')
ax1.set_xlabel('Date', fontsize=14, color='#ffd700')
ax1.set_ylabel('Nonfarm Payroll Employment (PAYEMS) (Thousands of People)', color='#ff1493', fontsize=14)
ax1.tick_params(axis='y', labelcolor='#ff1493', labelsize=12)
ax1.tick_params(axis='x', labelcolor='#ffd700', labelsize=12)

# Create the second y-axis for GDP
ax2 = ax1.twinx()
ax2.plot(merged_data['date'], merged_data['GDP'], color='#00ffff', label='GDP')
ax2.set_ylabel('GDP (Billions of Dollars)', color='#00ffff', fontsize=14)
ax2.tick_params(axis='y', labelcolor='#00ffff', labelsize=12)

# Set the title and add glow effects
plt.title('Nonfarm Payroll Employment (PAYEMS) vs GDP', fontsize=16, color='#ffd700')
mplcyberpunk.add_glow_effects()

# Adjust layout to ensure labels and title are well positioned
plt.tight_layout()

# Show the plot
plt.show()

import pandas as pd
from IPython.display import HTML

# Assuming 'merged_data' already has the necessary columns from your previous steps
# Calculate the Pearson correlation coefficient
correlation = merged_data['PAYEMS'].corr(merged_data['GDP'])

# Display the result with Cyberpunk style
HTML(f"""
<div style="background-color:#0d0f12; padding:10px; border-radius:10px; width: fit-content; margin: 10px auto;">
    <p style="color:#ff1493; font-size:20px; font-family: 'Courier New', Courier, monospace;">
        <strong>Pearson Correlation Coefficient:</strong>
        <span style="color:#00ffff;">{correlation:.5f}</span>
    </p>
</div>
""")

from IPython.display import HTML

# Custom CSS for Cyberpunk theme
cyberpunk_css = """
<style>
    body {
        background-color: #0a0a0a;
        color: #00ffcc;
        font-family: 'Courier New', Courier, monospace;
    }
    table {
        width: 100%;
        border-collapse: collapse;
    }
    th, td {
        border: 1px solid #ff007f;
        padding: 8px;
        text-align: center;
    }
    th {
        background-color: #002b36;
        color: #00ffcc;
    }
    tr:nth-child(even) {
        background-color: #003b46;
    }
    caption {
        caption-side: top;
        text-align: center;
        color: #ff007f;
        font-weight: bold;
    }
</style>
"""

# Combine the CSS with the summary HTML
styled_summary_html = cyberpunk_css + summary_html

# Display the styled summary
HTML(styled_summary_html)

import matplotlib.pyplot as plt
import seaborn as sns
import mplcyberpunk

# Apply the Cyberpunk style
plt.style.use("cyberpunk")

# Create the scatter plot
plt.figure(figsize=(12, 8))
sns.regplot(x='PAYEMS', y='GDP', data=merged_data, scatter_kws={'s': 10, 'color': '#00ffff'}, line_kws={'color': '#ff1493'})

# Set the labels and title with Cyberpunk colors
plt.xlabel('Nonfarm Payroll Employment (Thousands of People)', fontsize=14, color='#ff1493')
plt.ylabel('GDP (Billions of Dollars)', fontsize=14, color='#00ffff')
plt.title('Scatter Plot of Nonfarm Payroll Employment (PAYEMS) vs GDP', fontsize=16, color='#ffd700')

# Add some glow to the plot
mplcyberpunk.add_glow_effects()

# Show the plot
plt.show()

import matplotlib.pyplot as plt
import seaborn as sns
import statsmodels.api as sm
from IPython.display import HTML
import mplcyberpunk

# Apply the Cyberpunk style for all the plots
plt.style.use("cyberpunk")

# Create a figure and axes for the dashboard
fig, axs = plt.subplots(2, 2, figsize=(18, 14), facecolor='#000000')  # Set the background to black
plt.subplots_adjust(hspace=0.4, wspace=0.4)

# Plot 1: Nonfarm Payroll Employment (PAYEMS) vs GDP over time
axs[0, 0].plot(merged_data['date'], merged_data['PAYEMS'], color='#00ffff', label='Nonfarm Employment Rate', zorder=3)
axs[0, 0].plot(merged_data['date'], merged_data['GDP'], color='#ff1493', label='GDP', zorder=3)
axs[0, 0].set_facecolor('#000000')  # Set plot area background to true black
axs[0, 0].set_xlabel('Date', fontsize=18, color='white')
axs[0, 0].set_ylabel('Rate (%)', fontsize=18, color='white')
axs[0, 0].tick_params(axis='both', labelsize=14, colors='white')
axs[0, 0].spines['left'].set_color('white')
axs[0, 0].spines['bottom'].set_color('white')
axs[0, 0].spines['top'].set_color('white')
axs[0, 0].spines['right'].set_color('white')
axs[0, 0].set_title('Nonfarm Employment vs GDP Over Time', fontsize=22, color='white', pad=35)
axs[0, 0].legend(loc='upper left', fontsize=14, facecolor='#181818', edgecolor='white', labelcolor=['#00ffff', '#ff1493'])

# Plot 2: Scatter Plot with Regression Line (PAYEMS vs GDP)
sns.regplot(x='PAYEMS', y='GDP', data=merged_data, ax=axs[0, 1], scatter_kws={'s': 10, 'color': '#ff1493'}, line_kws={'color': '#00ffff'})
axs[0, 1].set_facecolor('#000000')  # Set plot area background to true black
axs[0, 1].set_xlabel('Nonfarm Employment (Thousands of People)', fontsize=18, color='white')
axs[0, 1].set_ylabel('GDP (Billions of Dollars)', fontsize=18, color='white')
axs[0, 1].tick_params(axis='both', labelsize=14, colors='white')
axs[0, 1].spines['left'].set_color('white')
axs[0, 1].spines['bottom'].set_color('white')
axs[0, 1].spines['top'].set_color('white')
axs[0, 1].spines['right'].set_color('white')
axs[0, 1].set_title('Scatter Plot of Nonfarm Employment vs GDP', fontsize=22, color='white', pad=35)

# Plot 3: Display Pearson Correlation Coefficient
correlation = merged_data['PAYEMS'].corr(merged_data['GDP'])
axs[1, 0].text(0.5, 0.5, f'Pearson Correlation Coefficient (Adjusted Data): {correlation:.2f}', transform=axs[1, 0].transAxes, fontsize=20, verticalalignment='center', horizontalalignment='center', bbox=dict(boxstyle='round', facecolor='#000000', edgecolor='#ff1493'))
axs[1, 0].axis('off')

# Plot 4: Linear Regression Summary
X = merged_data['PAYEMS']
y = merged_data['GDP']
X = sm.add_constant(X)  # Adds a constant term to the predictor
model = sm.OLS(y, X).fit()
summary_text = model.summary().as_text()
axs[1, 1].text(0.5, 0.5, f'Linear Regression Summary:\n\n{summary_text}', transform=axs[1, 1].transAxes, fontsize=10, color='white', horizontalalignment='center', verticalalignment='center', bbox=dict(facecolor='#000000', edgecolor='#ff1493', boxstyle='round,pad=0.5'))
axs[1, 1].axis('off')

# Adjust layout to prevent overlap
plt.tight_layout()

# Show the complete dashboard
mplcyberpunk.add_glow_effects()
plt.show()