Explorer des données avec des notebooks Jupyter et chDB

export CLICKHOUSE_USER=default
export CLICKHOUSE_PASSWORD=your_actual_password

pip install notebook

jupyter notebook

pip install chdb

import chdb

result = chdb.query("SELECT 'Hello, ClickHouse!' as message")
print(result)

import os
from dotenv import load_dotenv
import chdb
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.dates as mdates

# Load environment variables from .env file
load_dotenv()

username = os.environ.get('CLICKHOUSE_USER')
password = os.environ.get('CLICKHOUSE_PASSWORD')

query = f"""
SELECT 
    toYear(date) AS year,
    avg(price) AS avg_price
FROM remoteSecure(
'****.europe-west4.gcp.clickhouse.cloud',
default.pp_complete,
'{username}',
'{password}'
)
WHERE town = 'LONDON'
GROUP BY toYear(date)
ORDER BY year;
"""

df = chdb.query(query, "DataFrame")
df.head()

df.dtypes

year          uint16
avg_price    float64
dtype: object

plt.figure(figsize=(12, 6))
plt.plot(df['year'], df['avg_price'], marker='o')
plt.xlabel('Year')
plt.ylabel('Price (£)')
plt.title('Price of London property over time')

# Show every 2nd year to avoid crowding
years_to_show = df['year'][::2]  # Every 2nd year
plt.xticks(years_to_show, rotation=45)

plt.grid(True, alpha=0.3)
plt.tight_layout()
plt.show()

query = f"""
SELECT 
    toYear(date) AS year,
    sum(houses_sold)*1000
    FROM file('/Users/datasci/Desktop/housing_in_london_monthly_variables.csv')
WHERE area = 'city of london' AND houses_sold IS NOT NULL
GROUP BY toYear(date)
ORDER BY year;
"""

df_2 = chdb.query(query, "DataFrame")
df_2.head()

# Create a figure with two y-axes
fig, ax1 = plt.subplots(figsize=(14, 8))

# Plot houses sold on the left y-axis
color = 'tab:blue'
ax1.set_xlabel('Year')
ax1.set_ylabel('Houses Sold', color=color)
ax1.plot(df_2['year'], df_2['houses_sold'], marker='o', color=color, label='Houses Sold', linewidth=2)
ax1.tick_params(axis='y', labelcolor=color)
ax1.grid(True, alpha=0.3)

# Create a second y-axis for price data
ax2 = ax1.twinx()
color = 'tab:red'
ax2.set_ylabel('Average Price (£)', color=color)

# Plot price data up until 2019
ax2.plot(df[df['year'] <= 2019]['year'], df[df['year'] <= 2019]['avg_price'], marker='s', color=color, label='Average Price', linewidth=2)
ax2.tick_params(axis='y', labelcolor=color)

# Format price axis with currency formatting
ax2.yaxis.set_major_formatter(plt.FuncFormatter(lambda x, p: f'£{x:,.0f}'))

# Set title and show every 2nd year
plt.title('London Housing Market: Sales Volume vs Prices Over Time', fontsize=14, pad=20)

# Use years only up to 2019 for both datasets
all_years = sorted(list(set(df_2[df_2['year'] <= 2019]['year']).union(set(df[df['year'] <= 2019]['year']))))
years_to_show = all_years[::2]  # Every 2nd year
ax1.set_xticks(years_to_show)
ax1.set_xticklabels(years_to_show, rotation=45)

# Add legends
ax1.legend(loc='upper left')
ax2.legend(loc='upper right')

plt.tight_layout()
plt.show()