Created
August 1, 2024 04:28
-
-
Save ducnh1022/028db59c5a9cbf3ce7a89ad9f07649bd to your computer and use it in GitHub Desktop.
csvtobqdnh
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import pandas as pd | |
from google.cloud import bigquery | |
# Set up BigQuery client | |
client = bigquery.Client() | |
# Function to create temporary table from CSV | |
def create_temp_table_from_csv(dataset_id, table_name, csv_path): | |
# Read CSV into pandas DataFrame | |
df = pd.read_csv(csv_path) | |
# Generate schema from DataFrame | |
schema = [] | |
for column in df.columns: | |
dtype = df[column].dtype | |
if dtype == 'int64': | |
schema.append(f"{column} INT64") | |
elif dtype == 'float64': | |
schema.append(f"{column} FLOAT64") | |
elif dtype == 'bool': | |
schema.append(f"{column} BOOL") | |
else: | |
schema.append(f"{column} STRING") | |
# Create temporary table query | |
table_ref = client.dataset(dataset_id).table(table_name) | |
table = bigquery.Table(table_ref, schema=schema) | |
table.expires = 3600 # Set expiry time for the temporary table (optional) | |
client.create_table(table) # Create the temporary table | |
print(f"Temporary table {dataset_id}.{table_name} created successfully.") | |
# Example usage | |
if __name__ == "__main__": | |
dataset_id = "your_dataset" # Replace with your BigQuery dataset ID | |
table_name = "temp_table" # Replace with your desired temporary table name | |
csv_path = "path/to/your/file.csv" # Replace with the path to your CSV file | |
create_temp_table_from_csv(dataset_id, table_name, csv_path) |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment