Client Portal Get a Quote

CSV / Excel Data Analyzer

Instant EDA: column types, missing values, stats, histograms and correlations.

No upload

Loading tool…

Processing happens on your device using your browser's CPU/GPU. Results are kept only in this tab's memory and are wiped when you click “Clear” or close the page.

About CSV / Excel Data Analyzer

Drop a CSV or Excel file and get the exploratory data analysis you would normally write pandas code for: how many rows, which columns are numeric, text or dates, how many values are missing, and how each number column is distributed. Analysts, students and small business owners can size up a dataset in seconds. The file is read and analysed inside your browser, never uploaded.

How to use CSV / Excel Data Analyzer

  1. Drop a .csv, .tsv, .xlsx, .xls, .ods or .json file onto the box, or click to choose one.
  2. Read the overview strip: rows, columns, numeric columns, missing cells with a percentage, and duplicate rows.
  3. Open each column card for its detected type, unique count, and for numbers the mean, standard deviation, min, quartiles, median, max, sum and IQR outlier count.
  4. Scroll to the Pearson correlation matrix to see which number columns move together.
  5. Click Download summary (CSV) to keep the per-column statistics, and check the 100-row preview at the bottom.

What people use it for

  • Checking a sales or attendance export for blank cells and duplicate rows before you trust it
  • Getting quick descriptive statistics for a college data science assignment without writing code
  • Spotting outliers in an invoice or expense sheet through the IQR count and the histogram shape
  • Seeing whether marketing spend and revenue columns actually correlate before building a model

Good to know

Only the first sheet of an Excel workbook is read, and formulas are analysed as their stored values. A column counts as numeric when at least 90 percent of its filled values are numbers, so one stray text entry will not spoil it. Correlations cover the first 15 numeric columns. This describes your data; it does not clean it or predict anything.

Frequently asked questions

What exactly do I learn from the report?
Dataset size, each column's type, how much data is missing and where, the spread of every numeric column through quartiles and a histogram, likely outliers, the most frequent values in text columns, and how numeric columns correlate.
Is my file uploaded for analysis?
No. The spreadsheet is parsed and every statistic is computed by JavaScript in your browser. Nothing is sent to a server and nothing is kept once you close the tab.
What does the correlation matrix mean?
Each cell is a Pearson coefficient between two numeric columns, from -1 to +1. Amber means they rise together, blue means one falls as the other rises, and values near zero mean no linear relationship.
How large a file can it handle?
That depends on your device's memory rather than a fixed limit. Files with a few hundred thousand rows work on a laptop; on a phone, stick to smaller extracts.