import pandas as pd

# Read CSV/Parquet directly from cloud URIs
df = pd.read_csv("s3://bucket/data.csv")
df = pd.read_parquet("s3://bucket/data.parquet")
df = pd.read_json("gs://bucket/data.json")

# Compression is auto-detected
df = pd.read_csv("s3://bucket/data.csv.gz")  # Automatically decompressed

import fsspec
import pandas as pd

# Create fsspec filesystem with configuration
fs = fsspec.filesystem("s3", anon=False)  # Uses default credentials chain

# Open file through filesystem
with fs.open("s3://bucket/data.csv") as f:
    df = pd.read_csv(f)

# Or pass filesystem directly (recommended for performance)
df = pd.read_parquet(
    "s3://bucket/data.parquet",
    filesystem=fs,
    columns=["id", "value"],  # Column pruning reduces data transfer
    filters=[("date", ">=", "2024-01-01")]  # Row group filtering
)

import pyarrow.fs as fs
import pandas as pd

s3_fs = fs.S3FileSystem(region="us-east-1")

# Read with column filtering
df = pd.read_parquet(
    "bucket/data.parquet",  # Note: no s3:// prefix when using filesystem
    filesystem=s3_fs,
    columns=["id", "name", "value"]
)

# Write to cloud storage
df.to_parquet(
    "s3://bucket/output/",
    filesystem=s3_fs,
    partition_cols=["year", "month"]  # Partitioned write
)

import pandas as pd

df = pd.DataFrame({
    "id": [1, 2, 3],
    "year": [2024, 2024, 2023],
    "month": [1, 2, 12],
    "value": [100.0, 200.0, 150.0]
})

# Using fsspec
fs = fsspec.filesystem("s3")
df.to_parquet(
    "s3://bucket/output/",
    partition_cols=["year", "month"],
    filesystem=fs
)
# Output structure: s3://bucket/output/year=2024/month=1/part-0.parquet