From 0569030ba3ee9624f7b9a3ffb25831a9068fd917 Mon Sep 17 00:00:00 2001 From: Aseem Date: Wed, 8 Jan 2025 08:20:48 -0600 Subject: [PATCH 1/2] index doc sync with readme and other minor updates --- README.md | 4 ++-- docs/index.md | 13 +++++++++---- 2 files changed, 11 insertions(+), 6 deletions(-) diff --git a/README.md b/README.md index 8bbe3d5..6d2ad88 100644 --- a/README.md +++ b/README.md @@ -18,11 +18,11 @@ pip install pycatcher ### Basic Requirements * PyCatcher expects a Pandas DataFrame as an input for various outlier detection methods. It can convert Spark DataFrame to Pandas DataFrame at the data processing stage. -* First column in the dataframe must be a time period column (date in 'YYYY-MM-DD'/month in 'YYYY-MM'/year in 'YYYY' +* First column in the dataframe must be a time period column (date in 'YYYY-MM-DD'; month in 'YYYY-MM'; year in 'YYYY' format) and the last column a numeric column (sum or total count for the time period) to detect outliers using Seasonal Decomposition algorithms. * Last column must be a numeric column to detect outliers using Interquartile Range (IQR) and Moving Average algorithms. -* There is no need for any labeled observations (ground truth). Outliers are detected solely through +* At present, the package does not depend on labeled observations (ground truth). Outliers are detected solely through underlying algorithms (for example, seasonal-trend decomposition and dispersion methods like MAD or Z-Score).
diff --git a/docs/index.md b/docs/index.md index 4269e80..7684a80 100644 --- a/docs/index.md +++ b/docs/index.md @@ -15,10 +15,15 @@ quarter level time-series data. pip install pycatcher ``` -### DataFrame Arguments -* First column in the dataframe must be a date column ('YYYY-MM-DD') and the last column a numeric column -(sum or total count for the time period) to detect outliers using Seasonal Decomposition algorithms. -* Last column must be a numeric column to detect outliers using Moving Average and Z-score algorithm. +### Basic Requirements +* PyCatcher expects a Pandas DataFrame as an input for various outlier detection methods. It can convert Spark DataFrame +to Pandas DataFrame at the data processing stage. +* First column in the dataframe must be a time period column (date in 'YYYY-MM-DD'; month in 'YYYY-MM'; year in 'YYYY' +format) and the last column a numeric column (sum or total count for the time period) to detect outliers using +Seasonal Decomposition algorithms. +* Last column must be a numeric column to detect outliers using Interquartile Range (IQR) and Moving Average algorithms. +* At present, the package does not depend on labeled observations (ground truth). Outliers are detected solely through +underlying algorithms (for example, seasonal-trend decomposition and dispersion methods like MAD or Z-Score).
From 2d5bee5d8b9f177d4e48c44cc29fedb066c32c01 Mon Sep 17 00:00:00 2001 From: Aseem Date: Wed, 8 Jan 2025 08:25:12 -0600 Subject: [PATCH 2/2] version update --- README.md | 2 +- docs/index.md | 2 +- pyproject.toml | 2 +- 3 files changed, 3 insertions(+), 3 deletions(-) diff --git a/README.md b/README.md index 6d2ad88..6d79c82 100644 --- a/README.md +++ b/README.md @@ -22,7 +22,7 @@ to Pandas DataFrame at the data processing stage. format) and the last column a numeric column (sum or total count for the time period) to detect outliers using Seasonal Decomposition algorithms. * Last column must be a numeric column to detect outliers using Interquartile Range (IQR) and Moving Average algorithms. -* At present, the package does not depend on labeled observations (ground truth). Outliers are detected solely through +* At present, PyCatcher does not depend on labeled observations (ground truth). Outliers are detected solely through underlying algorithms (for example, seasonal-trend decomposition and dispersion methods like MAD or Z-Score).
diff --git a/docs/index.md b/docs/index.md index 7684a80..9ae2c8a 100644 --- a/docs/index.md +++ b/docs/index.md @@ -22,7 +22,7 @@ to Pandas DataFrame at the data processing stage. format) and the last column a numeric column (sum or total count for the time period) to detect outliers using Seasonal Decomposition algorithms. * Last column must be a numeric column to detect outliers using Interquartile Range (IQR) and Moving Average algorithms. -* At present, the package does not depend on labeled observations (ground truth). Outliers are detected solely through +* At present, PyCatcher does not depend on labeled observations (ground truth). Outliers are detected solely through underlying algorithms (for example, seasonal-trend decomposition and dispersion methods like MAD or Z-Score).
diff --git a/pyproject.toml b/pyproject.toml index 29c66da..815e73d 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -1,6 +1,6 @@ [tool.poetry] name = "pycatcher" -version = "0.0.62" +version = "0.0.63" description = "This package identifies outlier(s) for a given time-series dataset in simple steps. It supports day, week, month and quarter level time-series data." authors = ["Aseem Anand "] maintainers = ["Jagadish Pamarthi "]