xarray.dataset.dropna

Author: harshitha1201

xarray/core/dataset.py

@@ -5683,6 +5683,79 @@ def dropna(
             Which variables to check for missing values. By default, all
             variables in the dataset are checked.
 
+        Example
+        -------
+
+        # Sample dataset with missing values
+        >>> data = {
+        ...     "time": [0, 1, 2, 3],
+        ...     "temperature": [25.0, None, 27.5, 28.0],
+        ...     "humidity": [60.0, 65.0, None, 70.0],
+        ... }
+        >>> dataset = xr.Dataset(data)
+        # Print the original dataset
+        >>> dataset
+        <xarray.Dataset>
+        Dimensions:      (time: 4, temperature: 4, humidity: 4)
+        Coordinates:
+        * time         (time) int64 0 1 2 3
+        * temperature  (temperature) object 25.0 None 27.5 28.0
+        * humidity     (humidity) object 60.0 65.0 None 70.0
+        Data variables:
+            *empty*
+
+        # Drop rows with any missing values
+        >>> dataset_dropped_any = dataset.dropna(dim="time", how="any")
+        # Print the dataset after dropping rows with any missing values
+        >>> dataset_dropped_any
+        <xarray.Dataset>
+        Dimensions:      (time: 4, temperature: 4, humidity: 4)
+        Coordinates:
+        * time         (time) int64 0 1 2 3
+        * temperature  (temperature) object 25.0 None 27.5 28.0
+        * humidity     (humidity) object 60.0 65.0 None 70.0
+        Data variables:
+            *empty*
+
+        # Drop rows with all missing values
+        >>> dataset_dropped_all = dataset.dropna(dim="time", how="all")
+        # Print the dataset after dropping rows with all missing values
+        >>> dataset_dropped_all
+        <xarray.Dataset>
+        Dimensions:      (time: 0, temperature: 4, humidity: 4)
+        Coordinates:
+        * time         (time) int64
+        * temperature  (temperature) object 25.0 None 27.5 28.0
+        * humidity     (humidity) object 60.0 65.0 None 70.0
+        Data variables:
+            *empty*
+
+        # Drop rows with a threshold of non-missing values
+        >>> dataset_dropped_thresh = dataset.dropna(dim="time", thresh=2)
+        # Print the dataset after dropping rows with a threshold of non-missing values
+        >>> dataset_dropped_thresh
+        <xarray.Dataset>
+        Dimensions:      (time: 0, temperature: 4, humidity: 4)
+        Coordinates:
+        * time         (time) int64
+        * temperature  (temperature) object 25.0 None 27.5 28.0
+        * humidity     (humidity) object 60.0 65.0 None 70.0
+        Data variables:
+            *empty*
+
+        # Drop rows for a subset of variables
+        >>> dataset_dropped_subset = dataset.dropna(dim="time", subset=["temperature"])
+        # Print the dataset after dropping rows for a subset of variables
+        >>> dataset_dropped_subset
+        <xarray.Dataset>
+        Dimensions:      (time: 4, temperature: 4, humidity: 4)
+        Coordinates:
+        * time         (time) int64 0 1 2 3
+        * temperature  (temperature) object 25.0 None 27.5 28.0
+        * humidity     (humidity) object 60.0 65.0 None 70.0
+        Data variables:
+            *empty*
+
         Returns
         -------
         Dataset