!pip install google-cloud-storage

import pandas as pd
from google.cloud import storage

# Replace with your actual credentials and bucket/file details
credentials_json = {
    "type": "service_account",
    "project_id": "your-project-id",
    "private_key_id": "your-private-key-id",
    "private_key": "your-private-key",
    "client_email": "your-client-email",
    "client_id": "your-client-id",
    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
    "token_uri": "https://oauth2.googleapis.com/token",
    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
    "client_x509_cert_url": "your-client-x509-cert-url"
}
# Authenticate
client = storage.Client.from_service_account_info(credentials_json)
bucket = client.get_bucket(''''your-bucket-name'''')
blob = bucket.blob(''''your-file.csv'''')
# Download the file as a string
data = blob.download_as_string().decode(''''utf-8'''')
# Create DataFrame
df = pd.read_csv(pd.compat.StringIO(data))

print(df.head())

from google.cloud import storage
import pandas as pd

# Replace with your actual credentials and bucket details
credentials_json = {
    "type": "service_account",
    "project_id": "your-project-id",
    "private_key_id": "your-private-key-id",
    "private_key": "your-private-key",
    "client_email": "your-client-email",
    "client_id": "your-client-id",
    "auth_uri": "https://accounts.google.com/o/oauth2/auth",
    "token_uri": "https://oauth2.googleapis.com/token",
    "auth_provider_x509_cert_url": "https://www.googleapis.com/oauth2/v1/certs",
    "client_x509_cert_url": "your-client-x509-cert-url"
}

client = storage.Client.from_service_account_info(credentials_json)
bucket = client.get_bucket(''''your-bucket-name'''')

# List all files in the bucket
blobs = bucket.list_blobs(prefix=''''your-folder/'''')

# Read multiple CSV files into DataFrames
dfs = []
for blob in blobs:
    if blob.name.endswith(''''.csv''''):
        data = blob.download_as_string().decode(''''utf-8'''')
        df = pd.read_csv(pd.compat.StringIO(data))
        dfs.append(df)

# Combine all DataFrames into one
combined_df = pd.concat(dfs, ignore_index=True)
print(combined_df.head())