04. CSV

CSV

Comma-Separated Values (CSV) The file is a delimited text file where values ​​are separated by commas. Each line in the file is a data record.

Each record consists of one or more fields separated by commas.

CSVLoader

• CSV Load data one row per document.

Copy

from langchain_community.document_loaders.csv_loader import CSVLoader

# Create a CSV loader
loader = CSVLoader(file_path="./data/titanic.csv")

# load data
docs = loader.load()

print(len(docs))
print(docs[0].metadata)

Copy

891
{'source': './data/titanic.csv', 'row': 0}

Customizing CSV parsing and loading

See the csv module documentation for more information on supported csv args.

Copy

# Column information:
# PassengerId,Survived,Pclass,Name,Sex,Age,SibSp,Parch,Ticket,Fare,Cabin,Embarked

# CSV file path
loader = CSVLoader(
    file_path="./data/titanic.csv",
    csv_args={
        "delimiter": ",",  # separator
        "quotechar": '"',  # quote character
        "fieldnames": [
            "Passenger ID",
            "Survival (1: Survived, 0: Died)",
            "Passenger Class",
            "Name",
            "Sex",
            "Age",
            "Number of Siblings/Spouses Aboard",
            "Number of Parents/Children Aboard",
            "Ticket Number",
            "Fare",
            "Cabin",
            "Port of Embarkation",
        ],  # field name
    },
)

# load data
docs = loader.load()

# data output
print(docs[1].page_content)

Copy

Passenger ID: 1
Survival (1: Survived, 0: Died): 0
Passenger Class: 3
Name: Braund, Mr. Owen Harris
Sex: male
Age: 22
Number of Siblings/Spouses Aboard: 1
Number of Parents/Children Aboard: 0
Ticket Number: A/5 21171
Fare: 7.25
Cabin: 
Port of Embarkation: S

Use the source_column argument to specify the source of the document generated for each row. Otherwise, file_path is used as the source for all documents.

This is useful when using a chain of questions to answer questions using sources loaded from a CSV file.

Copy

loader = CSVLoader(
    file_path="./data/titanic.csv", source_column="PassengerId"
)  # Set up CSV loader, specify file path and source columns

docs = loader.load()  # load data

print(docs[1])  # data output

Copy

page_content='PassengerId: 2
Survived: 1
Pclass: 1
Name: Cumings, Mrs. John Bradley (Florence Briggs Thayer)
Sex: female
Age: 38
SibSp: 1
Parch: 0
Ticket: PC 17599
Fare: 71.2833
Cabin: C85
Embarked: C' metadata={'source': '2', 'row': 1}

UnstructuredCSVLoader

You can also load tables using UnstructuredCSVLoader. One advantage of using UnstructuredCSVLoader is that when used in "elements" mode, the metadata provides an HTML representation of the table.

Copy

from langchain_community.document_loaders.csv_loader import UnstructuredCSVLoader

# Creating an unstructured CSV loader instance
loader = UnstructuredCSVLoader(file_path="./data/titanic.csv", mode="elements")

# load document
docs = loader.load()

# Output HTML text metadata for the first document
print(docs[0].metadata["text_as_html"][:1000])

DataFrameLoader

• Output HTML text metadata for the first document

Copy

import pandas as pd

# Read CSV file
df = pd.read_csv("./data/titanic.csv")

Query the first 5 rows..

Copy

# The first five rows of the dataframe
df.head()

PassengerId

Survived

Pclass

Name

Sex

Age

SibSp

Parch

Ticket

Fare

Cabin

Embarked

0

1

0

3

Braund, Mr. Owen Harris

male

22.0

1

0

A/5 21171

7.2500

NaN

S

1

2

1

1

Cumings, Mrs. John Bradley (Florence Briggs Th...

female

38.0

1

0

PC 17599

71.2833

C85

C

2

3

1

3

Heikkinen, Miss. Laina

female

26.0

0

0

STON/O2. 3101282

7.9250

NaN

S

3

4

1

1

Futrelle, Mrs. Jacques Heath (Lily May Peel)

female

35.0

1

0

113803

53.1000

C123

S

4

5

0

3

Allen, Mr. William Henry

male

35.0

0

0

373450

8.0500

NaN

S

Copy

from langchain_community.document_loaders import DataFrameLoader

# Setting up a data frame loader, specifying page content columns
loader = DataFrameLoader(df, page_content_column="Name")

# Load Document
docs = loader.load()

# Data Output
print(docs[0].page_content)

# Output metadata
print(docs[0].metadata)

Copy

Braund, Mr. Owen Harris
{'PassengerId': 1, 'Survived': 0, 'Pclass': 3, 'Sex': 'male', 'Age': 22.0, 'SibSp': 1, 'Parch': 0, 'Ticket': 'A/5 21171', 'Fare': 7.25, 'Cabin': nan, 'Embarked': 'S'}

Copy

# Lazy loading for large tables, not loading the entire table into memory
for row in loader.lazy_load():
    print(row)
    break  # Print only the first row

Copy

page_content='Braund, Mr. Owen Harris' metadata={'PassengerId': 1, 'Survived': 0, 'Pclass': 3, 'Sex': 'male', 'Age': 22.0, 'SibSp': 1, 'Parch': 0, 'Ticket': 'A/5 21171', 'Fare': 7.25, 'Cabin': nan, 'Embarked': 'S'}