|
| 1 | +import typing |
| 2 | +from pyspark.sql.session import SparkSession |
| 3 | +from pyspark.sql.functions import udf as U |
| 4 | +from pyspark.sql.context import SQLContext |
| 5 | + |
| 6 | +udf = U |
| 7 | +spark: SparkSession |
| 8 | +sc = spark.sparkContext |
| 9 | +sqlContext: SQLContext |
| 10 | +sql = sqlContext.sql |
| 11 | +table = sqlContext.table |
| 12 | + |
| 13 | +def displayHTML(html): |
| 14 | + """ |
| 15 | + Display HTML data. |
| 16 | +
|
| 17 | + Parameters |
| 18 | + ---------- |
| 19 | + data : URL or HTML string |
| 20 | + If data is a URL, display the resource at that URL, the resource is loaded dynamically by the browser. |
| 21 | + Otherwise data should be the HTML to be displayed. |
| 22 | +
|
| 23 | + See also: |
| 24 | + IPython.display.HTML |
| 25 | + IPython.display.display_html |
| 26 | + """ |
| 27 | + ... |
| 28 | + |
| 29 | +def display(input=None, *args, **kwargs): |
| 30 | + """ |
| 31 | + Display plots or data. |
| 32 | +
|
| 33 | + Display plot: |
| 34 | + - display() # no-op |
| 35 | + - display(matplotlib.figure.Figure) |
| 36 | +
|
| 37 | + Display dataset: |
| 38 | + - display(spark.DataFrame) |
| 39 | + - display(list) # if list can be converted to DataFrame, e.g., list of named tuples |
| 40 | + - display(pandas.DataFrame) |
| 41 | + - display(koalas.DataFrame) |
| 42 | + - display(pyspark.pandas.DataFrame) |
| 43 | +
|
| 44 | + Display any other value that has a _repr_html_() method |
| 45 | +
|
| 46 | + For Spark 2.0 and 2.1: |
| 47 | + - display(DataFrame, streamName='optional', trigger=optional pyspark.sql.streaming.Trigger, |
| 48 | + checkpointLocation='optional') |
| 49 | +
|
| 50 | + For Spark 2.2+: |
| 51 | + - display(DataFrame, streamName='optional', trigger=optional interval like '1 second', |
| 52 | + checkpointLocation='optional') |
| 53 | + """ |
| 54 | + ... |
| 55 | + |
| 56 | +class dbutils: |
| 57 | + class credentials: |
| 58 | + """ |
| 59 | + Utilities for interacting with credentials within notebooks |
| 60 | + """ |
| 61 | + |
| 62 | + def assumeRole(role: str) -> bool: |
| 63 | + """ |
| 64 | + Sets the role ARN to assume when looking for credentials to authenticate with S3 |
| 65 | + """ |
| 66 | + ... |
| 67 | + def showCurrentRole() -> typing.List[str]: |
| 68 | + """ |
| 69 | + Shows the currently set role |
| 70 | + """ |
| 71 | + ... |
| 72 | + def showRoles() -> typing.List[str]: |
| 73 | + """ |
| 74 | + Shows the set of possibly assumed roles |
| 75 | + """ |
| 76 | + ... |
| 77 | + |
| 78 | + class data: |
| 79 | + """ |
| 80 | + Utilities for understanding and interacting with datasets (EXPERIMENTAL) |
| 81 | + """ |
| 82 | + |
| 83 | + def summarize(df: any, precise: bool) -> None: |
| 84 | + """ |
| 85 | + Summarize a Spark DataFrame and visualize the statistics to get quick insights |
| 86 | + """ |
| 87 | + ... |
| 88 | + |
| 89 | + class fs: |
| 90 | + """ |
| 91 | + Manipulates the Databricks filesystem (DBFS) from the console |
| 92 | + """ |
| 93 | + |
| 94 | + def cp(from_: str, to: str, recurse: bool = False) -> bool: |
| 95 | + """ |
| 96 | + Copies a file or directory, possibly across FileSystems |
| 97 | + """ |
| 98 | + ... |
| 99 | + def head(file: str, maxBytes: int = 65536) -> str: |
| 100 | + """ |
| 101 | + Returns up to the first 'maxBytes' bytes of the given file as a String encoded in UTF-8 |
| 102 | + """ |
| 103 | + ... |
| 104 | + def ls(dir: str) -> typing.List[str]: |
| 105 | + """ |
| 106 | + Lists the contents of a directory |
| 107 | + """ |
| 108 | + ... |
| 109 | + def mkdirs(dir: str) -> bool: |
| 110 | + """ |
| 111 | + Creates the given directory if it does not exist, also creating any necessary parent directories |
| 112 | + """ |
| 113 | + ... |
| 114 | + def mv(from_: str, to: str, recurse: bool = False) -> bool: |
| 115 | + """ |
| 116 | + Moves a file or directory, possibly across FileSystems |
| 117 | + """ |
| 118 | + ... |
| 119 | + def put(file: str, contents: str, overwrite: bool = False) -> bool: |
| 120 | + """ |
| 121 | + Writes the given String out to a file, encoded in UTF-8 |
| 122 | + """ |
| 123 | + ... |
| 124 | + def rm(dir: str, recurse: bool = False) -> bool: |
| 125 | + """ |
| 126 | + Removes a file or directory |
| 127 | + """ |
| 128 | + ... |
| 129 | + def mount( |
| 130 | + source: str, |
| 131 | + mountPoint: str, |
| 132 | + encryptionType: str = "", |
| 133 | + owner: str = "", |
| 134 | + extraConfigs: typing.Map[str, str] = {}, |
| 135 | + ) -> bool: |
| 136 | + """ |
| 137 | + Mounts the given source directory into DBFS at the given mount point |
| 138 | + """ |
| 139 | + ... |
| 140 | + def unmount(mountPoint: str) -> bool: |
| 141 | + """ |
| 142 | + Deletes a DBFS mount point |
| 143 | + """ |
| 144 | + ... |
| 145 | + def updateMount( |
| 146 | + source: str, |
| 147 | + mountPoint: str, |
| 148 | + encryptionType: str = "", |
| 149 | + owner: str = "", |
| 150 | + extraConfigs: typing.Map[str, str] = {}, |
| 151 | + ) -> bool: |
| 152 | + """ |
| 153 | + Similar to mount(), but updates an existing mount point (if present) instead of creating a new one |
| 154 | + """ |
| 155 | + ... |
| 156 | + def mounts() -> typing.List[str]: |
| 157 | + """ |
| 158 | + Displays information about what is mounted within DBFS |
| 159 | + """ |
| 160 | + ... |
| 161 | + def refreshMounts() -> bool: |
| 162 | + """ |
| 163 | + Forces all machines in this cluster to refresh their mount cache, ensuring they receive the most recent information |
| 164 | + """ |
| 165 | + ... |
| 166 | + |
| 167 | + class jobs: |
| 168 | + """ |
| 169 | + Utilities for leveraging jobs features |
| 170 | + """ |
| 171 | + |
| 172 | + class taskValues: |
| 173 | + """ |
| 174 | + Provides utilities for leveraging job task values |
| 175 | + """ |
| 176 | + |
| 177 | + def get( |
| 178 | + taskKey: str, key: str, default: any = None, debugValue: any = None |
| 179 | + ) -> None: |
| 180 | + """ |
| 181 | + Returns the latest task value that belongs to the current job run |
| 182 | + """ |
| 183 | + ... |
| 184 | + def set(key: str, value: any) -> None: |
| 185 | + """ |
| 186 | + Sets a task value on the current task run |
| 187 | + """ |
| 188 | + ... |
| 189 | + |
| 190 | + class library: |
| 191 | + """ |
| 192 | + Utilities for session isolated libraries |
| 193 | + """ |
| 194 | + |
| 195 | + def restartPython() -> None: |
| 196 | + """ |
| 197 | + Restart python process for the current notebook session |
| 198 | + """ |
| 199 | + ... |
| 200 | + |
| 201 | + class notebook: |
| 202 | + """ |
| 203 | + Utilities for the control flow of a notebook (EXPERIMENTAL) |
| 204 | + """ |
| 205 | + |
| 206 | + def exit(value: str) -> None: |
| 207 | + """ |
| 208 | + This method lets you exit a notebook with a value |
| 209 | + """ |
| 210 | + ... |
| 211 | + def run(path: str, timeoutSeconds: int, arguments: typing.Map[str, str]) -> str: |
| 212 | + """ |
| 213 | + This method runs a notebook and returns its exit value |
| 214 | + """ |
| 215 | + ... |
| 216 | + |
| 217 | + class secrets: |
| 218 | + """ |
| 219 | + Provides utilities for leveraging secrets within notebooks |
| 220 | + """ |
| 221 | + |
| 222 | + def get(scope: str, key: str) -> str: |
| 223 | + """ |
| 224 | + Gets the string representation of a secret value with scope and key |
| 225 | + """ |
| 226 | + ... |
| 227 | + def list(scope: str) -> typing.List[str]: |
| 228 | + """ |
| 229 | + Lists secret metadata for secrets within a scope |
| 230 | + """ |
| 231 | + ... |
| 232 | + def listScopes() -> typing.List[str]: |
| 233 | + """ |
| 234 | + Lists secret scopes |
| 235 | + """ |
| 236 | + ... |
| 237 | + |
| 238 | + class widgets: |
| 239 | + """ |
| 240 | + provides utilities for working with notebook widgets. You can create different types of widgets and get their bound value |
| 241 | + """ |
| 242 | + |
| 243 | + def get(name: str) -> str: |
| 244 | + """Returns the current value of a widget with give name. |
| 245 | +
|
| 246 | + :param name: Name of the argument to be accessed |
| 247 | + :return: Current value of the widget or default value |
| 248 | + """ |
| 249 | + ... |
| 250 | + def getArgument(name: str, defaultValue: typing.Optional[str] = None) -> str: |
| 251 | + """Returns the current value of a widget with give name. |
| 252 | +
|
| 253 | + :param name: Name of the argument to be accessed |
| 254 | + :param defaultValue: (Deprecated) default value |
| 255 | + :return: Current value of the widget or default value |
| 256 | + """ |
| 257 | + ... |
| 258 | + def text(name: str, defaultValue: str, label: str = None): |
| 259 | + """Creates a text input widget with given name, default value and optional label for |
| 260 | + display |
| 261 | + :param name: Name of argument associated with the new input widget |
| 262 | + :param defaultValue: Default value of the input widget |
| 263 | + :param label: Optional label string for display in notebook and dashboard |
| 264 | + """ |
| 265 | + ... |
| 266 | + def dropdown( |
| 267 | + name: str, defaultValue: str, choices: typing.List[str], label: str = None |
| 268 | + ): |
| 269 | + """Creates a dropdown input widget with given specification. |
| 270 | + :param name: Name of argument associated with the new input widget |
| 271 | + :param defaultValue: Default value of the input widget (must be one of choices) |
| 272 | + :param choices: List of choices for the dropdown input widget |
| 273 | + :param label: Optional label string for display in notebook and dashboard |
| 274 | + """ |
| 275 | + ... |
| 276 | + def combobox( |
| 277 | + name: str, |
| 278 | + defaultValue: str, |
| 279 | + choices: typing.List[str], |
| 280 | + label: typing.Optional[str] = None, |
| 281 | + ): |
| 282 | + """Creates a combobox input widget with given specification. |
| 283 | + :param name: Name of argument associated with the new input widget |
| 284 | + :param defaultValue: Default value of the input widget |
| 285 | + :param choices: List of choices for the dropdown input widget |
| 286 | + :param label: Optional label string for display in notebook and dashboard |
| 287 | + """ |
| 288 | + ... |
| 289 | + def multiselect( |
| 290 | + name: str, |
| 291 | + defaultValue: str, |
| 292 | + choices: typing.List[str], |
| 293 | + label: typing.Optional[str] = None, |
| 294 | + ): |
| 295 | + """Creates a multiselect input widget with given specification. |
| 296 | + :param name: Name of argument associated with the new input widget |
| 297 | + :param defaultValue: Default value of the input widget (must be one of choices) |
| 298 | + :param choices: List of choices for the dropdown input widget |
| 299 | + :param label: Optional label string for display in notebook and dashboard |
| 300 | + """ |
| 301 | + ... |
| 302 | + def remove(name: str): |
| 303 | + """Removes given input widget. If widget does not exist it will throw an error. |
| 304 | + :param name: Name of argument associated with input widget to be removed |
| 305 | + """ |
| 306 | + ... |
| 307 | + def removeAll(): |
| 308 | + """Removes all input widgets in the notebook.""" |
| 309 | + ... |
| 310 | + @property |
| 311 | + def meta() -> MetaUtils: |
| 312 | + """ |
| 313 | + Methods to hook into the compiler (EXPERIMENTAL) |
| 314 | + """ |
| 315 | + ... |
| 316 | + |
| 317 | +getArgument = dbutils.widgets.getArgument |
0 commit comments