blob: de8cae2955796ccd49516b8c842bdd888fae8c36 [file] [log] [blame] [view]
<!---
Licensed to the Apache Software Foundation (ASF) under one
or more contributor license agreements. See the NOTICE file
distributed with this work for additional information
regarding copyright ownership. The ASF licenses this file
to you under the Apache License, Version 2.0 (the
"License"); you may not use this file except in compliance
with the License. You may obtain a copy of the License at
http://www.apache.org/licenses/LICENSE-2.0
Unless required by applicable law or agreed to in writing,
software distributed under the License is distributed on an
"AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY
KIND, either express or implied. See the License for the
specific language governing permissions and limitations
under the License.
-->
# Example Usage
## Update `Cargo.toml`
Add the following to your `Cargo.toml` file:
```toml
datafusion = "8.0.0"
tokio = "1.0"
```
## Run a SQL query against data stored in a CSV:
```rust
use datafusion::prelude::*;
#[tokio::main]
async fn main() -> datafusion::error::Result<()> {
// register the table
let ctx = SessionContext::new();
ctx.register_csv("example", "tests/example.csv", CsvReadOptions::new()).await?;
// create a plan to run a SQL query
let df = ctx.sql("SELECT a, MIN(b) FROM example GROUP BY a LIMIT 100").await?;
// execute and print results
df.show().await?;
Ok(())
}
```
## Use the DataFrame API to process data stored in a CSV:
```rust
use datafusion::prelude::*;
#[tokio::main]
async fn main() -> datafusion::error::Result<()> {
// create the dataframe
let ctx = SessionContext::new();
let df = ctx.read_csv("tests/example.csv", CsvReadOptions::new()).await?;
let df = df.filter(col("a").lt_eq(col("b")))?
.aggregate(vec![col("a")], vec![min(col("b"))])?;
// execute and print results
df.show_limit(100).await?;
Ok(())
}
```
## Output from both examples
```text
+---+--------+
| a | MIN(b) |
+---+--------+
| 1 | 2 |
+---+--------+
```