Examine a dataset with pandas and seaborn¶
│ │ │ │Convert to a pandas DataFrame¶
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │ [2]:
│ │ │ │ @@ -932,15 +932,15 @@
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │ [5]:
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │ -<seaborn.axisgrid.PairGrid at 0x7f79de890850>
│ │ │ │ +<seaborn.axisgrid.PairGrid at 0x7f00ce57a690>
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │ 
│ │ │ │ @@ -1338,26 +1338,26 @@
│ │ │ │ [0. , 0. , 0. ],
│ │ │ │ [0. , 0. , 0. ],
│ │ │ │ [0. , 0.01612903, 0. ],
│ │ │ │ [0.33333333, 0.35 , 0.23333333],
│ │ │ │ [0.93548387, 0.85483871, 0.82258065]])
│ │ │ │ Coordinates:
│ │ │ │ * location (location) <U2 'IA' 'IN' 'IL'
│ │ │ │ - * month (month) int64 1 2 3 4 5 6 7 8 9 10 11 12
│ │ │ │ @@ -1338,26 +1338,26 @@
│ │ │ │ [0. , 0. , 0. ],
│ │ │ │ [0. , 0. , 0. ],
│ │ │ │ [0. , 0.01612903, 0. ],
│ │ │ │ [0.33333333, 0.35 , 0.23333333],
│ │ │ │ [0.93548387, 0.85483871, 0.82258065]])
│ │ │ │ Coordinates:
│ │ │ │ * location (location) <U2 'IA' 'IN' 'IL'
│ │ │ │ - * month (month) int64 1 2 3 4 5 6 7 8 9 10 11 12- location(location)<U2'IA' 'IN' 'IL'
array(['IA', 'IN', 'IL'], dtype='<U2')
- month(month)int641 2 3 4 5 6 7 8 9 10 11 12
array([ 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12])
- locationPandasIndex
PandasIndex(Index(['IA', 'IN', 'IL'], dtype='object', name='location'))
- monthPandasIndex
PandasIndex(Int64Index([1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12], dtype='int64', name='month'))
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │ @@ -1863,18 +1863,18 @@
│ │ │ │ Dimensions: (time: 731, location: 3)
│ │ │ │ Coordinates:
│ │ │ │ * time (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2001-12-31
│ │ │ │ * location (location) <U2 'IA' 'IN' 'IL'
│ │ │ │ month (time) int64 1 1 1 1 1 1 1 1 1 ... 12 12 12 12 12 12 12 12 12
│ │ │ │ Data variables:
│ │ │ │ some_missing (time, location) float64 nan nan nan ... 2.063 -1.346 -4.544
│ │ │ │ - filled (time, location) float64 -5.163 -4.216 ... -1.346 -4.544
│ │ │ │
│ │ │ │ [7]:
│ │ │ │ freeze.to_pandas().plot()
│ │ │ │ location
PandasIndex
PandasIndex(Index(['IA', 'IN', 'IL'], dtype='object', name='location'))
│ │ │ │
│ │ │ │
│ │ │ │ "
│ │ │ │ │ │ ],
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ "\n",
│ │ │ │ │ │ "Dimensions: (time: 731, location: 3)\n",
│ │ │ │ │ │ "Coordinates:\n",
│ │ │ │ │ │ " * time (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2001-12-31\n",
│ │ │ │ │ │ " * location (location) \n",
│ │ │ │ │ │ @@ -587,18 +587,18 @@
│ │ │ │ │ │ "execution_count": 3,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:47:32.682065Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:47:32.652629Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:10.352471Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:10.352005Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:10.379258Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:10.377838Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:50.239317Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:50.238780Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:48:50.357012Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:48:50.340945Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/html": [
│ │ │ │ │ │ "\n",
│ │ │ │ │ │ "array([[0.9516129 , 0.88709677, 0.93548387],\n",
│ │ │ │ │ │ " [0.84210526, 0.71929825, 0.77192982],\n",
│ │ │ │ │ │ " [0.24193548, 0.12903226, 0.16129032],\n",
│ │ │ │ │ │ " [0. , 0. , 0. ],\n",
│ │ │ │ │ │ @@ -1236,18 +1236,18 @@
│ │ │ │ │ │ "execution_count": 7,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:48:13.131247Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:48:12.924985Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:14.740652Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:14.740161Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:15.411991Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:15.410685Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:57.150785Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:57.150266Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:48:58.092927Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:48:58.076889Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ ""
│ │ │ │ │ │ @@ -1284,18 +1284,18 @@
│ │ │ │ │ │ "execution_count": 8,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:48:08.498259Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:48:08.210890Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:15.432946Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:15.432513Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:16.914744Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:16.900564Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:58.118696Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:58.118187Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:48:59.436949Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:48:59.420876Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ ""
│ │ │ │ │ │ @@ -1349,18 +1349,18 @@
│ │ │ │ │ │ "execution_count": 9,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:49:34.855086Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:49:34.406439Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:16.936575Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:16.936113Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:18.422716Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:18.406676Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:59.462847Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:59.462374Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:49:00.397412Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:49:00.389739Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ ""
│ │ │ │ │ │ @@ -1408,18 +1408,18 @@
│ │ │ │ │ │ "execution_count": 10,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:50:09.144586Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:50:08.734682Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:18.448278Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:18.447857Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:19.986743Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:19.970659Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:49:00.405433Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:49:00.404984Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:49:01.346023Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:49:01.344878Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ ""
│ │ │ │ │ │ @@ -1477,18 +1477,18 @@
│ │ │ │ │ │ "execution_count": 11,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:51:40.279299Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:51:40.220342Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:20.011117Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:20.010657Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:20.156405Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:20.155156Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:49:01.351743Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:49:01.351339Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:49:01.471890Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:49:01.470800Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/html": [
│ │ │ │ │ │ " "
│ │ │ │ │ │ ],
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ "\n",
│ │ │ │ │ │ "Dimensions: (time: 731, location: 3)\n",
│ │ │ │ │ │ "Coordinates:\n",
│ │ │ │ │ │ " * time (time) datetime64[ns] 2000-01-01 2000-01-02 ... 2001-12-31\n",
│ │ │ │ │ │ " * location (location) \n",
│ │ │ │ │ │ @@ -2052,18 +2052,18 @@
│ │ │ │ │ │ "execution_count": 13,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:52:14.867866Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:52:14.449684Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:20.204382Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:20.203981Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:20.920225Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:20.918744Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:49:01.504389Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:49:01.503966Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:49:02.433236Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:49:02.426071Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ ""
│ │ │ ├── ./usr/share/doc/python-xarray-doc/html/getting-started-guide/quick-overview.html
│ │ │ │ @@ -310,15 +310,15 @@
│ │ │ │
│ │ │ │
│ │ │ │ [12]:
│ │ │ │ df = both.sel(time="2000").mean("location").reset_coords(drop=True).to_dataframe()
│ │ │ │ df.head()
│ │ │ │ ├── html2text {}
│ │ │ │ │ @@ -157,15 +157,15 @@
│ │ │ │ │
│ │ │ │ │ [../_images/examples_weather-data_7_1.png]
│ │ │ │ │
│ │ │ │ │ **** Visualize using seaborn¶ ****
│ │ │ │ │ [5]:
│ │ │ │ │ sns.pairplot(df.reset_index(), vars=ds.data_vars)
│ │ │ │ │ [5]:
│ │ │ │ │ -
│ │ │ │ │ +
│ │ │ │ │ [../_images/examples_weather-data_9_1.png]
│ │ │ │ │
│ │ │ │ │ ***** Probability of freeze by calendar month¶ *****
│ │ │ │ │ [6]:
│ │ │ │ │ freeze = (ds["tmin"] <= 0).groupby("time.month").mean("time")
│ │ │ │ │ freeze
│ │ │ │ │ [6]:
│ │ │ ├── ./usr/share/doc/python-xarray-doc/html/examples/weather-data.ipynb.gz
│ │ │ │ ├── weather-data.ipynb
│ │ │ │ │ ├── Pretty-printed
│ │ │ │ │ │┄ Similarity: 0.9992323118860381%
│ │ │ │ │ │┄ Differences: {"'cells'": "{1: {'metadata': {'execution': {'iopub.execute_input': '2024-01-12T09:48:44.386940Z', "
│ │ │ │ │ │┄ "'iopub.status.busy': '2024-01-12T09:48:44.386362Z', 'iopub.status.idle': "
│ │ │ │ │ │┄ "'2024-01-12T09:48:50.068914Z', 'shell.execute_reply': "
│ │ │ │ │ │┄ "'2024-01-12T09:48:50.052867Z'}}, 'outputs': {0: {'data': {'text/html': {insert: "
│ │ │ │ │ │┄ '[(370, " tmax (time, location) float64 12.98 3.31 6.779 ... 6.636 3.343 '
│ │ │ │ │ │┄ "3.805 \n",
│ │ │ │ │ │ @@ -701,18 +701,18 @@
│ │ │ │ │ │ "execution_count": 4,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:47:34.617042Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:47:34.282605Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:10.384989Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:10.384532Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:11.015413Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:11.002672Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:50.387042Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:50.386514Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:48:52.012937Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:48:51.996884Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ ""
│ │ │ │ │ │ @@ -749,25 +749,25 @@
│ │ │ │ │ │ "execution_count": 5,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:47:37.643175Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:47:37.202479Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:11.040490Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:11.039998Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:14.604220Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:14.602763Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:52.038688Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:52.038204Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:48:56.900874Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:48:56.884923Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ - ""
│ │ │ │ │ │ + ""
│ │ │ │ │ │ ]
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution_count": 5,
│ │ │ │ │ │ "metadata": {},
│ │ │ │ │ │ "output_type": "execute_result"
│ │ │ │ │ │ },
│ │ │ │ │ │ {
│ │ │ │ │ │ @@ -797,18 +797,18 @@
│ │ │ │ │ │ "execution_count": 6,
│ │ │ │ │ │ "metadata": {
│ │ │ │ │ │ "ExecuteTime": {
│ │ │ │ │ │ "end_time": "2020-01-27T15:48:11.241224Z",
│ │ │ │ │ │ "start_time": "2020-01-27T15:48:11.211156Z"
│ │ │ │ │ │ },
│ │ │ │ │ │ "execution": {
│ │ │ │ │ │ - "iopub.execute_input": "2025-02-13T15:49:14.616868Z",
│ │ │ │ │ │ - "iopub.status.busy": "2025-02-13T15:49:14.616404Z",
│ │ │ │ │ │ - "iopub.status.idle": "2025-02-13T15:49:14.732081Z",
│ │ │ │ │ │ - "shell.execute_reply": "2025-02-13T15:49:14.730717Z"
│ │ │ │ │ │ + "iopub.execute_input": "2024-01-12T09:48:56.928204Z",
│ │ │ │ │ │ + "iopub.status.busy": "2024-01-12T09:48:56.927292Z",
│ │ │ │ │ │ + "iopub.status.idle": "2024-01-12T09:48:57.120947Z",
│ │ │ │ │ │ + "shell.execute_reply": "2024-01-12T09:48:57.104857Z"
│ │ │ │ │ │ }
│ │ │ │ │ │ },
│ │ │ │ │ │ "outputs": [
│ │ │ │ │ │ {
│ │ │ │ │ │ "data": {
│ │ │ │ │ │ "text/html": [
│ │ │ │ │ │ "
"
│ │ │ │ │ │ ],
│ │ │ │ │ │ "text/plain": [
│ │ │ │ │ │ "Plotting¶
│ │ │ │Visualizing your datasets is quick and convenient:
│ │ │ │In [37]: data.plot()
│ │ │ │ -Out[37]: <matplotlib.collections.QuadMesh at 0x7f073f9fdfd0>
│ │ │ │ +Out[37]: <matplotlib.collections.QuadMesh at 0x7f56058667d0>
│ │ │ │ 
│ │ │ │ Note the automatic labeling with names and units. Our effort in adding metadata attributes has paid off! Many aspects of these figures are customizable: see Plotting.
│ │ │ │pandas¶
│ │ │ │ ├── html2text {} │ │ │ │ │ @@ -269,15 +269,15 @@ │ │ │ │ │ Coordinates: │ │ │ │ │ * x (x) int64 10 20 │ │ │ │ │ Dimensions without coordinates: y │ │ │ │ │ │ │ │ │ │ ***** Plotting¶ ***** │ │ │ │ │ Visualizing your datasets is quick and convenient: │ │ │ │ │ In [37]: data.plot() │ │ │ │ │ -Out[37]:You’ll notice that printing a dataset still shows a preview of array values, │ │ │ │ even if they are actually Dask arrays. We can do this quickly with Dask because │ │ │ │ we only need to compute the first few values (typically from the first block). │ │ │ │ To reveal the true nature of an array, print a DataArray:
│ │ │ │In [3]: ds.temperature
│ │ │ │ Out[3]:
│ │ │ │ <xarray.DataArray 'temperature' (time: 30, latitude: 180, longitude: 180)>
│ │ │ │ -dask.array<open_dataset-39b7b670ad00b8e2e3cc5e2b10b5c905temperature, shape=(30, 180, 180), dtype=float64, chunksize=(10, 180, 180), chunktype=numpy.ndarray>
│ │ │ │ +dask.array<open_dataset-e465d2fa847582f6a280739021dc3613temperature, shape=(30, 180, 180), dtype=float64, chunksize=(10, 180, 180), chunktype=numpy.ndarray>
│ │ │ │ Coordinates:
│ │ │ │ * time (time) datetime64[ns] 2015-01-01 2015-01-02 ... 2015-01-30
│ │ │ │ * longitude (longitude) int64 0 1 2 3 4 5 6 7 ... 173 174 175 176 177 178 179
│ │ │ │ * latitude (latitude) float64 89.5 88.5 87.5 86.5 ... -87.5 -88.5 -89.5
│ │ │ │ Once you’ve manipulated a Dask array, you can still write a dataset too big to │ │ │ │ @@ -138,16 +138,17 @@ │ │ │ │ # or distributed.progress when using the distributed scheduler │ │ │ │ In [6]: delayed_obj = ds.to_netcdf("manipulated-example-data.nc", compute=False) │ │ │ │ │ │ │ │ In [7]: with ProgressBar(): │ │ │ │ ...: results = delayed_obj.compute() │ │ │ │ ...: │ │ │ │ │ │ │ │ -[ ] | 0% Completed | 15.02 ms │ │ │ │ -[########################################] | 100% Completed | 122.88 ms │ │ │ │ +[ ] | 0% Completed | 10.29 ms │ │ │ │ +[######################### ] | 62% Completed | 118.03 ms │ │ │ │ +[########################################] | 100% Completed | 226.13 ms │ │ │ │ │ │ │ │ │ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │
│ │ │ │ Note
│ │ │ │When using Dask’s distributed scheduler to write NETCDF4 files,
│ │ │ │ it may be necessary to set the environment variable HDF5_USE_FILE_LOCKING=FALSE
│ │ │ │ to avoid competing locks within the HDF5 SWMR file locking scheme. Note that
│ │ │ │ ├── html2text {}
│ │ │ │ │ @@ -76,15 +76,15 @@
│ │ │ │ │ Youâll notice that printing a dataset still shows a preview of array values,
│ │ │ │ │ even if they are actually Dask arrays. We can do this quickly with Dask because
│ │ │ │ │ we only need to compute the first few values (typically from the first block).
│ │ │ │ │ To reveal the true nature of an array, print a DataArray:
│ │ │ │ │ In [3]: ds.temperature
│ │ │ │ │ Out[3]:
│ │ │ │ │ ds.pipe(func)) instead of
│ │ │ │ simply calling it (e.g., func(ds)). This allows you to write pipelines for
│ │ │ │ transforming your data (using “method chaining”) instead of writing hard to
│ │ │ │ follow nested function calls:
# these lines are equivalent, but with pipe we can make the logic flow
│ │ │ │ # entirely from left to right
│ │ │ │ In [60]: plt.plot((2 * ds.temperature.sel(x=0)).mean("y"))
│ │ │ │ -Out[60]: [<matplotlib.lines.Line2D at 0x7f070fca15d0>]
│ │ │ │ +Out[60]: [<matplotlib.lines.Line2D at 0x7f55d5461350>]
│ │ │ │
│ │ │ │ In [61]: (ds.temperature.sel(x=0).pipe(lambda x: 2 * x).mean("y").pipe(plt.plot))
│ │ │ │ -Out[61]: [<matplotlib.lines.Line2D at 0x7f070f5933d0>]
│ │ │ │ +Out[61]: [<matplotlib.lines.Line2D at 0x7f55d54be410>]
│ │ │ │ Both pipe and assign replicate the pandas methods of the same names
│ │ │ │ (DataFrame.pipe and
│ │ │ │ DataFrame.assign).
With xarray, there is no performance penalty for creating new datasets, even if
│ │ │ │ variables are lazily loaded from a file on disk. Creating new objects instead
│ │ │ │ ├── html2text {}
│ │ │ │ │ @@ -574,19 +574,19 @@
│ │ │ │ │ There is also the pipe() method that allows you to use a method call with an
│ │ │ │ │ external function (e.g., ds.pipe(func)) instead of simply calling it (e.g.,
│ │ │ │ │ func(ds)). This allows you to write pipelines for transforming your data (using
│ │ │ │ │ âmethod chainingâ) instead of writing hard to follow nested function calls:
│ │ │ │ │ # these lines are equivalent, but with pipe we can make the logic flow
│ │ │ │ │ # entirely from left to right
│ │ │ │ │ In [60]: plt.plot((2 * ds.temperature.sel(x=0)).mean("y"))
│ │ │ │ │ -Out[60]: [
│ │ │ │ Additional keyword arguments can be passed to scipy’s functions.
│ │ │ │# fill 0 for the outside of the original coordinates.
│ │ │ │ In [21]: da.interp(x=np.linspace(-0.5, 1.5, 10), kwargs={"fill_value": 0.0})
│ │ │ │ Out[21]:
│ │ │ │ @@ -615,15 +615,15 @@
│ │ │ │ 858 f"Dimensions {invalid} do not exist. Expected one or more of {dims}"
│ │ │ │ 859 )
│ │ │ │ 861 return indexers
│ │ │ │ 863 elif missing_dims == "warn":
│ │ │ │ 864
│ │ │ │ 865 # don't modify input
│ │ │ │
│ │ │ │ -ValueError: Dimensions {'lat', 'lon'} do not exist. Expected one or more of Frozen({'x': 3, 'y': 4})
│ │ │ │ +ValueError: Dimensions {'lon', 'lat'} do not exist. Expected one or more of Frozen({'x': 3, 'y': 4})
│ │ │ │
│ │ │ │ In [63]: dsi.air.plot(ax=axes[1])
│ │ │ │ ---------------------------------------------------------------------------
│ │ │ │ NameError Traceback (most recent call last)
│ │ │ │ Cell In [63], line 1
│ │ │ │ ----> 1 dsi.air.plot(ax=axes[1])
│ │ │ │ ├── html2text {}
│ │ │ │ │ @@ -165,26 +165,26 @@
│ │ │ │ │ ....: np.sin(np.linspace(0, 2 * np.pi, 10)),
│ │ │ │ │ ....: dims="x",
│ │ │ │ │ ....: coords={"x": np.linspace(0, 1, 10)},
│ │ │ │ │ ....: )
│ │ │ │ │ ....:
│ │ │ │ │
│ │ │ │ │ In [17]: da.plot.line("o", label="original")
│ │ │ │ │ -Out[17]: []
│ │ │ │ │ +Out[17]: []
│ │ │ │ │
│ │ │ │ │ In [18]: da.interp(x=np.linspace(0, 1, 100)).plot.line(label="linear
│ │ │ │ │ (default)")
│ │ │ │ │ -Out[18]: []
│ │ │ │ │ +Out[18]: []
│ │ │ │ │
│ │ │ │ │ In [19]: da.interp(x=np.linspace(0, 1, 100), method="cubic").plot.line
│ │ │ │ │ (label="cubic")
│ │ │ │ │ -Out[19]: []
│ │ │ │ │ +Out[19]: []
│ │ │ │ │
│ │ │ │ │ In [20]: plt.legend()
│ │ │ │ │ -Out[20]:
│ │ │ │ │ +Out[20]:
│ │ │ │ │ [../_images/interpolation_sample1.png]
│ │ │ │ │ Additional keyword arguments can be passed to scipyâs functions.
│ │ │ │ │ # fill 0 for the outside of the original coordinates.
│ │ │ │ │ In [21]: da.interp(x=np.linspace(-0.5, 1.5, 10), kwargs={"fill_value": 0.0})
│ │ │ │ │ Out[21]:
│ │ │ │ │
│ │ │ │ │ array([ 0. , 0. , 0. , 0.814, 0.604, -0.604, -0.814, 0. , 0. ,
│ │ │ │ │ @@ -558,15 +558,15 @@
│ │ │ │ │ of {dims}"
│ │ │ │ │ 859 )
│ │ │ │ │ 861 return indexers
│ │ │ │ │ 863 elif missing_dims == "warn":
│ │ │ │ │ 864
│ │ │ │ │ 865 # don't modify input
│ │ │ │ │
│ │ │ │ │ -ValueError: Dimensions {'lat', 'lon'} do not exist. Expected one or more of
│ │ │ │ │ +ValueError: Dimensions {'lon', 'lat'} do not exist. Expected one or more of
│ │ │ │ │ Frozen({'x': 3, 'y': 4})
│ │ │ │ │
│ │ │ │ │ In [63]: dsi.air.plot(ax=axes[1])
│ │ │ │ │ ---------------------------------------------------------------------------
│ │ │ │ │ NameError Traceback (most recent call last)
│ │ │ │ │ Cell In [63], line 1
│ │ │ │ │ ----> 1 dsi.air.plot(ax=axes[1])
│ │ │ ├── ./usr/share/doc/python-xarray-doc/html/user-guide/plotting.html
│ │ │ │ @@ -643,15 +643,15 @@
│ │ │ │ --> 186 raise KeyError(key)
│ │ │ │ 188 ref_name, var_name = split_key
│ │ │ │ 189 ref_var = variables[ref_name]
│ │ │ │
│ │ │ │ KeyError: 'lat'
│ │ │ │
│ │ │ │ In [51]: b.plot()
│ │ │ │ -Out[51]: [<matplotlib.lines.Line2D at 0x7f07c3fe13d0>]
│ │ │ │ +Out[51]: [<matplotlib.lines.Line2D at 0x7f5685e7e750>]
│ │ │ │ 
│ │ │ │ Other types of plot¶
│ │ │ │There are several other options for plotting 2D data.
│ │ │ │ @@ -1205,104 +1205,104 @@ │ │ │ │ * y (y) float64 0.0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 1.0 │ │ │ │ * z (z) int64 0 1 2 3 │ │ │ │ * w (w) <U5 'one' 'two' 'three' 'five' │ │ │ │ Attributes: │ │ │ │ units: Aunits │ │ │ │ │ │ │ │ In [99]: ds.A.plot.scatter(x="y") │ │ │ │ -Out[99]: <matplotlib.collections.PathCollection at 0x7f07c3edf290> │ │ │ │ +Out[99]: <matplotlib.collections.PathCollection at 0x7f5685d2bed0> │ │ │ │ │ │ │ │ │ │ │ │
│ │ │ │ Same plot can be displayed using the dataset:
│ │ │ │In [100]: ds.plot.scatter(x="y", y="A")
│ │ │ │ -Out[100]: <matplotlib.collections.PathCollection at 0x7f07c3d9c310>
│ │ │ │ +Out[100]: <matplotlib.collections.PathCollection at 0x7f5685c6ba90>
│ │ │ │ 
│ │ │ │ Now suppose we want to scatter the A DataArray against the B DataArray
In [101]: ds.plot.scatter(x="A", y="B")
│ │ │ │ -Out[101]: <matplotlib.collections.PathCollection at 0x7f07c3e56690>
│ │ │ │ +Out[101]: <matplotlib.collections.PathCollection at 0x7f5685cd6cd0>
│ │ │ │ 
│ │ │ │ The hue kwarg lets you vary the color by variable value
In [102]: ds.plot.scatter(x="A", y="B", hue="w")
│ │ │ │ -Out[102]: <matplotlib.collections.PathCollection at 0x7f07c3e24310>
│ │ │ │ +Out[102]: <matplotlib.collections.PathCollection at 0x7f5685c38c10>
│ │ │ │ 
│ │ │ │ You can force a legend instead of a colorbar by setting add_legend=True, add_colorbar=False.
In [103]: ds.plot.scatter(x="A", y="B", hue="w", add_legend=True, add_colorbar=False)
│ │ │ │ -Out[103]: <matplotlib.collections.PathCollection at 0x7f070d587290>
│ │ │ │ +Out[103]: <matplotlib.collections.PathCollection at 0x7f55d343ccd0>
│ │ │ │ 
│ │ │ │ In [104]: ds.plot.scatter(x="A", y="B", hue="w", add_legend=False, add_colorbar=True)
│ │ │ │ -Out[104]: <matplotlib.collections.PathCollection at 0x7f07c3e405d0>
│ │ │ │ +Out[104]: <matplotlib.collections.PathCollection at 0x7f55d3475dd0>
│ │ │ │ 
│ │ │ │ The markersize kwarg lets you vary the point’s size by variable value.
│ │ │ │ You can additionally pass size_norm to control how the variable’s values are mapped to point sizes.
In [105]: ds.plot.scatter(x="A", y="B", hue="y", markersize="z")
│ │ │ │ -Out[105]: <matplotlib.collections.PathCollection at 0x7f070d5c7290>
│ │ │ │ +Out[105]: <matplotlib.collections.PathCollection at 0x7f55d32d1a50>
│ │ │ │ 
│ │ │ │ The z kwarg lets you plot the data along the z-axis as well.
In [106]: ds.plot.scatter(x="A", y="B", z="z", hue="y", markersize="x")
│ │ │ │ -Out[106]: <mpl_toolkits.mplot3d.art3d.Path3DCollection at 0x7f070d430350>
│ │ │ │ +Out[106]: <mpl_toolkits.mplot3d.art3d.Path3DCollection at 0x7f55d32f0190>
│ │ │ │ 
│ │ │ │ Faceting is also possible
│ │ │ │In [107]: ds.plot.scatter(x="A", y="B", hue="y", markersize="x", row="x", col="w")
│ │ │ │ -Out[107]: <xarray.plot.facetgrid.FacetGrid at 0x7f070d4b4290>
│ │ │ │ +Out[107]: <xarray.plot.facetgrid.FacetGrid at 0x7f55d6b7a050>
│ │ │ │ 
│ │ │ │ And adding the z-axis
│ │ │ │In [108]: ds.plot.scatter(x="A", y="B", z="z", hue="y", markersize="x", row="x", col="w")
│ │ │ │ -Out[108]: <xarray.plot.facetgrid.FacetGrid at 0x7f070cf70350>
│ │ │ │ +Out[108]: <xarray.plot.facetgrid.FacetGrid at 0x7f55d305c610>
│ │ │ │ 
│ │ │ │ For more advanced scatter plots, we recommend converting the relevant data variables
│ │ │ │ to a pandas DataFrame and using the extensive plotting capabilities of seaborn.
Quiver¶
│ │ │ │Visualizing vector fields is supported with quiver plots:
│ │ │ │In [109]: ds.isel(w=1, z=1).plot.quiver(x="x", y="y", u="A", v="B")
│ │ │ │ -Out[109]: <matplotlib.quiver.Quiver at 0x7f070d2de8d0>
│ │ │ │ +Out[109]: <matplotlib.quiver.Quiver at 0x7f55d2c8cb90>
│ │ │ │ 
│ │ │ │ where u and v denote the x and y direction components of the arrow vectors. Again, faceting is also possible:
In [110]: ds.plot.quiver(x="x", y="y", u="A", v="B", col="w", row="z", scale=4)
│ │ │ │ -Out[110]: <xarray.plot.facetgrid.FacetGrid at 0x7f070f6a9550>
│ │ │ │ +Out[110]: <xarray.plot.facetgrid.FacetGrid at 0x7f55d2d61bd0>
│ │ │ │ 
│ │ │ │ scale is required for faceted quiver plots.
│ │ │ │ The scale determines the number of data units per arrow length unit, i.e. a smaller scale parameter makes the arrow longer.
Streamplot¶
│ │ │ │Visualizing vector fields is also supported with streamline plots:
│ │ │ │In [111]: ds.isel(w=1, z=1).plot.streamplot(x="x", y="y", u="A", v="B")
│ │ │ │ -Out[111]: <matplotlib.collections.LineCollection at 0x7f07c3e0fe10>
│ │ │ │ +Out[111]: <matplotlib.collections.LineCollection at 0x7f55d29493d0>
│ │ │ │ 
│ │ │ │ where u and v denote the x and y direction components of the vectors tangent to the streamlines.
│ │ │ │ Again, faceting is also possible:
In [112]: ds.plot.streamplot(x="x", y="y", u="A", v="B", col="w", row="z")
│ │ │ │ -Out[112]: <xarray.plot.facetgrid.FacetGrid at 0x7f070d07d590>
│ │ │ │ +Out[112]: <xarray.plot.facetgrid.FacetGrid at 0x7f55d2772690>
│ │ │ │ 
│ │ │ │ 
│ │ │ │ 