Skip to content

Add DataFrame.IO tests with separators in data #6301

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 2 commits into from
Closed

Add DataFrame.IO tests with separators in data #6301

Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
f74d1ab
Add DataFrame.IO tests with separators in data
dakersnar Aug 23, 2022
d72df26
Add test where comma is in header
dakersnar Aug 23, 2022
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
181 changes: 181 additions & 0 deletions test/Microsoft.Data.Analysis.Tests/DataFrame.IOTests.cs
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -465,6 +465,187 @@ void Verify(DataFrame df, bool verifyDataTypes)
Verify(df, false);
}

[Fact]
public void TestReadCsvWithCommaSeparatorsInData()
{
string data = @"Name,Age,Description
Paul,34,""Paul lives in Vermont, VA.""
Victor,29,""Victor: Funny guy""
Maria,31,";

void Verify(DataFrame df)
{
Assert.Equal(3, df.Rows.Count);
Assert.Equal(3, df.Columns.Count);

Assert.True(typeof(string) == df.Columns[0].DataType);
Assert.True(typeof(int) == df.Columns[1].DataType);
Assert.True(typeof(string) == df.Columns[2].DataType);


Assert.Equal("Name", df.Columns[0].Name);
Assert.Equal("Age", df.Columns[1].Name);
Assert.Equal("Description", df.Columns[2].Name);
VerifyColumnTypes(df);

var paulRow = df.Rows[0];
Assert.Equal("Paul", paulRow[0]);
Assert.Equal(34, paulRow[1]);
Assert.Equal("Paul lives in Vermont, VA.", paulRow[2]);

var victorRow = df.Rows[1];
Assert.Equal("Victor", victorRow[0]);
Assert.Equal(29, victorRow[1]);
Assert.Equal("Victor: Funny guy", victorRow[2]);

var mariaRow = df.Rows[2];
Assert.Equal("Maria", mariaRow[0]);
Assert.Equal(31, mariaRow[1]);
Assert.Equal("", mariaRow[2]);
}

DataFrame df = DataFrame.LoadCsv(GetStream(data), dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) });
Verify(df);
df = DataFrame.LoadCsvFromString(data, dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) });
Verify(df);
}

[Fact]
public void TestReadCsvWithColonSeparatorsInData()
{
string data = @"Name:Age:Description
Paul:34:""Paul lives in Vermont, VA.""
Victor:29:""Victor: Funny guy""
Maria:31:";
void Verify(DataFrame df)
{
Assert.Equal(3, df.Rows.Count);
Assert.Equal(3, df.Columns.Count);

Assert.True(typeof(string) == df.Columns[0].DataType);
Assert.True(typeof(int) == df.Columns[1].DataType);
Assert.True(typeof(string) == df.Columns[2].DataType);


Assert.Equal("Name", df.Columns[0].Name);
Assert.Equal("Age", df.Columns[1].Name);
Assert.Equal("Description", df.Columns[2].Name);
VerifyColumnTypes(df);

var paulRow = df.Rows[0];
Assert.Equal("Paul", paulRow[0]);
Assert.Equal(34, paulRow[1]);
Assert.Equal("Paul lives in Vermont, VA.", paulRow[2]);

var victorRow = df.Rows[1];
Assert.Equal("Victor", victorRow[0]);
Assert.Equal(29, victorRow[1]);
Assert.Equal("Victor: Funny guy", victorRow[2]);

var mariaRow = df.Rows[2];
Assert.Equal("Maria", mariaRow[0]);
Assert.Equal(31, mariaRow[1]);
Assert.Equal("", mariaRow[2]);
}

DataFrame df = DataFrame.LoadCsv(GetStream(data), dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) }, separator: ':');
Verify(df);
df = DataFrame.LoadCsvFromString(data, dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) }, separator: ':');
Verify(df);
}

[Fact]
public void TestReadCsvWithCommaSeparatorsInHeaderData()
{
string data = @"""Na,me"",Age,Description
Paul,34,""Paul lives in Vermont, VA.""
Victor,29,""Victor: Funny guy""
Maria,31,";

void Verify(DataFrame df)
{
Assert.Equal(3, df.Rows.Count);
Assert.Equal(3, df.Columns.Count);

Assert.True(typeof(string) == df.Columns[0].DataType);
Assert.True(typeof(int) == df.Columns[1].DataType);
Assert.True(typeof(string) == df.Columns[2].DataType);


Assert.Equal("Na,me", df.Columns[0].Name);
Assert.Equal("Age", df.Columns[1].Name);
Assert.Equal("Description", df.Columns[2].Name);
VerifyColumnTypes(df);

var paulRow = df.Rows[0];
Assert.Equal("Paul", paulRow[0]);
Assert.Equal(34, paulRow[1]);
Assert.Equal("Paul lives in Vermont, VA.", paulRow[2]);

var victorRow = df.Rows[1];
Assert.Equal("Victor", victorRow[0]);
Assert.Equal(29, victorRow[1]);
Assert.Equal("Victor: Funny guy", victorRow[2]);

var mariaRow = df.Rows[2];
Assert.Equal("Maria", mariaRow[0]);
Assert.Equal(31, mariaRow[1]);
Assert.Equal("", mariaRow[2]);
}

DataFrame df = DataFrame.LoadCsv(GetStream(data), dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) });
Verify(df);
df = DataFrame.LoadCsvFromString(data, dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) });
Verify(df);
}

[Fact]
public void TestReadCsvWithNewlinesInData()
{
string data = @"Name,Age,Description
Paul,34,""Paul lives in Vermont
VA.""
Victor,29,""Victor: Funny guy""
Maria,31,";

void Verify(DataFrame df)
{
Assert.Equal(3, df.Rows.Count);
Assert.Equal(3, df.Columns.Count);

Assert.True(typeof(string) == df.Columns[0].DataType);
Assert.True(typeof(int) == df.Columns[1].DataType);
Assert.True(typeof(string) == df.Columns[2].DataType);


Assert.Equal("Name", df.Columns[0].Name);
Assert.Equal("Age", df.Columns[1].Name);
Assert.Equal("Description", df.Columns[2].Name);
VerifyColumnTypes(df);

var paulRow = df.Rows[0];
Assert.Equal("Paul", paulRow[0]);
Assert.Equal(34, paulRow[1]);
Assert.Equal(@"Paul lives in Vermont
VA.", paulRow[2]);

var victorRow = df.Rows[1];
Assert.Equal("Victor", victorRow[0]);
Assert.Equal(29, victorRow[1]);
Assert.Equal("Victor: Funny guy", victorRow[2]);

var mariaRow = df.Rows[2];
Assert.Equal("Maria", mariaRow[0]);
Assert.Equal(31, mariaRow[1]);
Assert.Equal("", mariaRow[2]);
}

DataFrame df = DataFrame.LoadCsv(GetStream(data), dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) });
Verify(df);
df = DataFrame.LoadCsvFromString(data, dataTypes: new Type[] { typeof(string), typeof(int), typeof(string) });
Verify(df);
}

[Fact]
public void TestReadCsvWithPipeSeparator()
{
Expand Down