Skip to main content

Documentation Index

Fetch the complete documentation index at: https://mintlify.com/Gurneet1928/TryMLEasy/llms.txt

Use this file to discover all available pages before exploring further.

TryMLEasy begins its workflow on the main page (home_page.py), where you upload the CSV dataset you want to work with. This is the very first step — everything from feature selection through model training depends on the file you provide here. Once uploaded, your data flows through a series of guided pages that take you from raw CSV all the way to trained model results, with no code required.

​
File Requirements

TryMLEasy reads your dataset using pandas.read_csv(), so the file must be a valid comma-separated values (.csv) file. Beyond the format itself, keep the following constraints in mind before uploading:
  • Format: .csv files only. Other formats (Excel, JSON, Parquet) are not accepted by the uploader widget.
  • Columns: All feature and target columns used during model training must be numeric. The app does not encode or transform categorical text columns automatically.
  • Headers: Your file should include a header row — column names are used throughout the feature selection and results pages.
  • Size: No explicit file size limit is enforced by the application, though very large files may slow down the browser interface.
TryMLEasy currently supports numerical columns only. If your dataset contains categorical string columns (e.g., "male"/"female" or "yes"/"no"), you must encode them as numbers (e.g., 0/1) before uploading. Columns with mixed or object dtypes may cause errors during training.

​
Uploading Your File

The main page presents a single file uploader widget. Follow these steps to get your dataset into TryMLEasy:
1

Open TryMLEasy

Launch the application in your browser. If you are running it locally, navigate to http://localhost:8501. If you are using a hosted deployment, open the provided cloud URL.
2

Click Browse Files

On the main page, locate the file uploader labelled “Upload your dataset in a .csv file format.” Click the Browse files button (or drag and drop your file directly onto the widget).
3

Select your .csv file

In the file picker dialog that opens, navigate to your .csv file and select it. The uploader accepts only .csv files — other extensions will be rejected.
4

Confirm the file appears

After selecting a file, its name will appear below the uploader widget and the progress bar will update. The Next button is disabled while no file is loaded; it becomes enabled automatically once a valid CSV file is detected.
5

Click Next to proceed

Click the Next button. TryMLEasy reads the file into a pandas DataFrame (pd.read_csv(dataset)) and stores it in session state (st.session_state.got_file). You will be taken to the Show Dataset preview page.

​
Reviewing Your Dataset

After clicking Next, you land on the Show Dataset page (pages/1_show_dataset.py). This page renders your full DataFrame using st.dataframe() with use_container_width=True, giving you a wide, scrollable, interactive table directly in the browser. Use this view to:
  • Scroll horizontally to confirm all expected columns are present.
  • Scroll vertically to spot obvious data issues like missing rows or misaligned values.
  • Verify column names — these are the names you will use when selecting features and a target column on the next page.
Two navigation buttons are available at the bottom of the page:
  • Back (Dataset Upload) — returns you to the main page so you can upload a different file.
  • Next (Feature Selection) — advances to the Feature Selection page where you configure your ML pipeline.

​
Using the Sample Dataset

The TryMLEasy repository includes a ready-made sample_data.csv file in its root directory. This is a wine quality dataset with 12 fully numeric columns — ideal for testing the full TryMLEasy workflow end to end without preparing your own data first. The first few rows look like this: 
fixed acidity,volatile acidity,citric acid,residual sugar,chlorides,free sulfur dioxide,total sulfur dioxide,density,pH,sulphates,alcohol,quality
7.4,0.7,0.0,1.9,0.076,11.0,34.0,0.9978,3.51,0.56,9.4,5
7.8,0.88,0.0,2.6,0.098,25.0,67.0,0.9968,3.2,0.68,9.8,5
7.8,0.76,0.04,2.3,0.092,15.0,54.0,0.997,3.26,0.65,9.8,5
To use it:
  1. Download sample_data.csv from the TryMLEasy GitHub repository.
  2. Upload it on the main page using the steps above.
  3. Use any of the 11 input columns as features and quality as the target for a regression task, or explore classification by binning the quality scores beforehand.

​
Session State and Page Refreshes

TryMLEasy stores your uploaded dataset in st.session_state.got_file. This means the DataFrame persists as you navigate between pages within the same browser session — you do not need to re-upload when moving from Feature Selection back to Dataset view, for example. However, if you refresh the browser page or close and reopen the tab, Streamlit resets the session state entirely. The got_file key will be None again, and all downstream pages (Show Dataset, Feature Selection, etc.) will lose access to the data. If this happens, simply return to the main page and re-upload your file.
Before uploading, take a moment to clean your dataset in a tool like Excel, Google Sheets, or a Jupyter notebook. Specifically: remove or fill NaN values (TryMLEasy does not impute missing data automatically), encode all categorical columns as integers, and drop any ID or index columns that should not be used as features. A clean upload makes every subsequent step faster and error-free.

Build docs developers (and LLMs) love

Get started for freeTalk to us