Release v1.0.0 (#272)

* ✨ Add min_count parameter to the base_processor. * ✨ Add `disable_auto_summary` config. * ✨ Allows custom average types, logs to an array for easy access to the last epoch. * 💥 Introducing breaking changes, rename package name to kashgari. * 🔊 Adding migration guide.
BrikerMan · Oct 18, 2019 · 822169e · 822169e
1 parent 7d7c819
commit 822169e
Show file tree

Hide file tree

Showing 13 changed files with 190 additions and 35 deletions.
diff --git a/README.md b/README.md
@@ -73,17 +73,17 @@ There are also articles and posts that illustrate how to use Kashgari:
 
 ### Requirements and Installation
 
-🎉🎉🎉 We renamed the tf.keras version as **kashgari-tf** 🎉🎉🎉
+🎉🎉🎉 We renamed again for consistency and clarity. From now on, it is all `kashgari`. 🎉🎉🎉
 
-The project is based on TensorFlow 1.14.0 and Python 3.6+, because it is 2019 and type hinting is cool.
+The project is based on Python 3.6+, because it is 2019 and type hinting is cool.
 
-```bash
-pip install kashgari-tf
-# CPU
-pip install tensorflow==1.14.0
-# GPU
-pip install tensorflow-gpu==1.14.0
-```
+| Backend          | pypi version                           | desc            |
+| ---------------- | -------------------------------------- | --------------- |
+| TensorFlow 2.x   | `pip install 'kashgari>=2.0.0'`        | coming soon     |
+| TensorFlow 1.14+ | `pip install 'kashgari>=1.0.0,<2.0.0'` | current version |
+| Keras            | `pip install 'kashgari<1.0.0'`         | legacy version  |
+
+[Find more info about the name changing.](https://github.com/BrikerMan/Kashgari/releases/tag/v1.0.0)
 
 ### Example Usage
 

diff --git a/kashgari/__init__.py b/kashgari/__init__.py
@@ -35,4 +35,6 @@
 from kashgari import utils
 from kashgari import callbacks
 
-import tensorflow as tf
+from kashgari import migeration
+
+migeration.show_migration_guide()
diff --git a/kashgari/callbacks.py b/kashgari/callbacks.py
@@ -16,7 +16,8 @@
 
 class EvalCallBack(keras.callbacks.Callback):
 
-    def __init__(self, kash_model: BaseModel, valid_x, valid_y, step=5, batch_size=256):
+    def __init__(self, kash_model: BaseModel, valid_x, valid_y,
+                 step=5, batch_size=256, average='weighted'):
         """
         Evaluate callback, calculate precision, recall and f1
         Args:
@@ -32,9 +33,8 @@ def __init__(self, kash_model: BaseModel, valid_x, valid_y, step=5, batch_size=2
         self.valid_y = valid_y
         self.step = step
         self.batch_size = batch_size
-        self.logs = {}
-
-        self.average = 'weighted'
+        self.average = average
+        self.logs = []
 
     def on_epoch_end(self, epoch, logs=None):
         if (epoch + 1) % self.step == 0:
@@ -51,15 +51,13 @@ def on_epoch_end(self, epoch, logs=None):
                 recall = metrics.recall_score(y_true, y_pred, average=self.average)
                 f1 = metrics.f1_score(y_true, y_pred, average=self.average)
 
-            self.logs[epoch] = {
+            self.logs.append({
                 'precision': precision,
                 'recall': recall,
                 'f1': f1
-            }
+            })
             print(f"\nepoch: {epoch} precision: {precision:.6f}, recall: {recall:.6f}, f1: {f1:.6f}")
 
 
 if __name__ == "__main__":
     print("Hello world")
-    config_path = '/Users/brikerman/Desktop/python/Kashgari/tests/test-data/bert/bert_config.json'
-    check_point_path = '/Users/brikerman/Desktop/python/Kashgari/tests/test-data/bert/bert_model.ckpt'
diff --git a/kashgari/embeddings/gpt_2_embedding.py b/kashgari/embeddings/gpt_2_embedding.py
@@ -95,7 +95,8 @@ def _build_model(self, **kwargs):
             model = gpt2.load_trained_model_from_checkpoint(config_path,
                                                             checkpoint_path,
                                                             self.sequence_length)
-            model.summary()
+            if not kashgari.config.disable_auto_summary:
+                model.summary()
             self.embed_model = model
         # if self.token_count == 0:
         #     logging.debug('need to build after build_word2idx')

diff --git a/kashgari/macros.py b/kashgari/macros.py
@@ -29,6 +29,7 @@ class Config(object):
 
     def __init__(self):
         self._use_cudnn_cell = False
+        self.disable_auto_summary = False
 
         if tf.test.is_gpu_available(cuda_only=True):
             logging.warning("CUDA GPU available, you can set `kashgari.config.use_cudnn_cell = True` to use CuDNNCell. "

diff --git a/kashgari/migeration.py b/kashgari/migeration.py
@@ -0,0 +1,43 @@
+# encoding: utf-8
+
+# author: BrikerMan
+# contact: [email protected]
+# blog: https://eliyar.biz
+
+# file: migration.py
+# time: 2:31 下午
+import subprocess
+import logging
+
+
+guide = """
+╭─────────────────────────────────────────────────────────────────────────╮
+│ ◎ ○ ○ ░░░░░░░░░░░░░░░░░░░░░  Important Message  ░░░░░░░░░░░░░░░░░░░░░░░░│
+├─────────────────────────────────────────────────────────────────────────┤
+│                                                                         │
+│              We renamed again for consistency and clarity.              │
+│                   From now on, it is all `kashgari`.                    │
+│  Changelog: https://github.com/BrikerMan/Kashgari/releases/tag/v1.0.0   │
+│                                                                         │
+│         | Backend          | pypi version   | desc           |          │
+│         | ---------------- | -------------- | -------------- |          │
+│         | TensorFlow 2.x   | kashgari 2.x.x | coming soon    |          │
+│         | TensorFlow 1.14+ | kashgari 1.x.x |                |          │
+│         | Keras            | kashgari 0.x.x | legacy version |          │
+│                                                                         │
+╰─────────────────────────────────────────────────────────────────────────╯
+"""
+
+
+def show_migration_guide():
+    requirements = subprocess.getoutput("pip freeze")
+    for package in requirements.splitlines():
+        if '==' in package:
+            package_name, package_version = package.split('==')
+            if package_name == 'kashgari-tf':
+                logging.warning(guide)
+
+
+if __name__ == "__main__":
+    show_migration_guide()
+    print("hello, world")
diff --git a/kashgari/processors/base_processor.py b/kashgari/processors/base_processor.py
@@ -45,6 +45,8 @@ def __init__(self, **kwargs):
 
         self.sequence_length = kwargs.get('sequence_length', None)
 
+        self.min_count = kwargs.get('min_count', 3)
+
     def info(self):
         return {
             'class_name': self.__class__.__name__,
@@ -65,13 +67,12 @@ def info(self):
     def analyze_corpus(self,
                        corpus: Union[List[List[str]]],
                        labels: Union[List[List[str]], List[str]],
-                       min_count: int = 3,
                        force: bool = False):
         rec_len = sorted([len(seq) for seq in corpus])[int(0.95 * len(corpus))]
         self.dataset_info['RECOMMEND_LEN'] = rec_len
 
         if len(self.token2idx) == 0 or force:
-            self._build_token_dict(corpus, min_count)
+            self._build_token_dict(corpus, self.min_count)
         if len(self.label2idx) == 0 or force:
             self._build_label_dict(labels)
 
@@ -103,7 +104,7 @@ def _build_token_dict(self, corpus: List[List[str]], min_count: int = 3):
         token2count = collections.OrderedDict(sorted_token2count)
 
         for token, token_count in token2count.items():
-            if token not in token2idx and token_count > min_count:
+            if token not in token2idx and token_count >= min_count:
                 token2idx[token] = len(token2idx)
 
         self.token2idx = token2idx

diff --git a/kashgari/tasks/base_model.py b/kashgari/tasks/base_model.py
@@ -383,7 +383,8 @@ def compile_model(self, **kwargs):
             kwargs['metrics'] = ['accuracy']
 
         self.tf_model.compile(**kwargs)
-        self.tf_model.summary()
+        if not kashgari.config.disable_auto_summary:
+            self.tf_model.summary()
 
     def predict(self,
                 x_data,

diff --git a/kashgari/version.py b/kashgari/version.py
@@ -7,4 +7,4 @@
 # file: __version__.py.py
 # time: 2019-05-20 16:32
 
-__version__ = '0.5.4'
+__version__ = '1.0.0'
diff --git a/mkdocs/docs/about/release-notes.md b/mkdocs/docs/about/release-notes.md
@@ -16,6 +16,31 @@ pip show kashgari-tf
 
 ## Current Release
 
+### [1.0.0] - 
+
+Unfortunately, we have to change the package name for clarity and consistency. Here is the new naming sytle.
+
+| Backend          | pypi version   | desc           |
+| ---------------- | -------------- | -------------- |
+| TensorFlow 2.x   | kashgari 2.x.x | coming soon    |
+| TensorFlow 1.14+ | kashgari 1.x.x |                |
+| Keras            | kashgari 0.x.x | legacy version |
+
+Here is how the existing versions changes
+
+| Supported Backend | Kashgari Versions | Kahgsari-tf Version |
+| ----------------- | ----------------- | ------------------- |
+| TensorFlow 2.x    | kashgari 2.x.x    | -                   |
+| TensorFlow 1.14+  | kashgari 1.0.1    | -                   |
+| TensorFlow 1.14+  | kashgari 1.0.0    | 0.5.5               |
+| TensorFlow 1.14+  | -                 | 0.5.4               |
+| TensorFlow 1.14+  | -                 | 0.5.3               |
+| TensorFlow 1.14+  | -                 | 0.5.2               |
+| TensorFlow 1.14+  | -                 | 0.5.1               |
+| Keras (legacy)    | kashgari 0.2.6    | -                   |
+| Keras (legacy)    | kashgari 0.2.5    | -                   |
+| Keras (legacy)    | kashgari 0.x.x    | -                   |
+
 ### [0.5.4] - 2019.09.30
 
 - ✨ Add shuffle parameter to fit function ([#249])
@@ -113,6 +138,7 @@ pip show kashgari-tf
 - fix classification model evaluate result output
 - change test settings
 
+[1.0.0]: https://github.com/BrikerMan/Kashgari/compare/v0.5.4...v1.0.0
 [0.5.4]: https://github.com/BrikerMan/Kashgari/compare/v0.5.3...v0.5.4
 [0.5.3]: https://github.com/BrikerMan/Kashgari/compare/v0.5.2...v0.5.3
 [0.5.2]: https://github.com/BrikerMan/Kashgari/compare/v0.5.1...v0.5.2

diff --git a/mkdocs/docs/index.md b/mkdocs/docs/index.md
@@ -64,17 +64,17 @@ There are also articles and posts that illustrate how to use Kashgari:
 
 ### Requirements and Installation
 
-🎉🎉🎉 We renamed the tf.keras version as **kashgari-tf** 🎉🎉🎉
+🎉🎉🎉 We renamed again for consistency and clarity. From now on, it is all `kashgari`. 🎉🎉🎉
 
-The project is based on TenorFlow 1.14.0 and Python 3.6+, because it is 2019 and type hints is cool.
+The project is based on Python 3.6+, because it is 2019 and type hinting is cool.
 
-```bash
-pip install kashgari-tf
-# CPU
-pip install tensorflow==1.14.0
-# GPU
-pip install tensorflow-gpu==1.14.0
-```
+| Backend          | pypi version                           | desc            |
+| ---------------- | -------------------------------------- | --------------- |
+| TensorFlow 2.x   | `pip install 'kashgari>=2.0.0'`        | coming soon     |
+| TensorFlow 1.14+ | `pip install 'kashgari>=1.0.0,<2.0.0'` | current version |
+| Keras            | `pip install 'kashgari<1.0.0'`         | legacy version  |
+
+[Find more info about the name changing.](https://github.com/BrikerMan/Kashgari/releases/tag/v1.0.0)
 
 ### Example Usage
 

diff --git a/setup.py b/setup.py
@@ -35,7 +35,7 @@ def find_version(*file_paths):
     raise RuntimeError("Unable to find version string.")
 
 
-__name__ = 'kashgari-tf'
+__name__ = 'kashgari'
 __author__ = "BrikerMan"
 __copyright__ = "Copyright 2018, BrikerMan"
 __credits__ = []
@@ -79,4 +79,4 @@ def find_version(*file_paths):
 )
 
 if __name__ == "__main__":
-    print("Hello world")
+    print("Hello world")
diff --git a/setup.tf.py b/setup.tf.py
@@ -0,0 +1,82 @@
+#!/usr/bin/env python
+# encoding: utf-8
+"""
+@author: BrikerMan
+@contact: [email protected]
+@blog: https://eliyar.biz
+
+@version: 1.0
+@license: Apache Licence
+@file: setup.py
+@time: 2019-01-24 16:42
+
+"""
+import codecs
+import os
+import pathlib
+import re
+
+from setuptools import find_packages, setup
+
+HERE = pathlib.Path(__file__).parent
+
+
+def read(*parts):
+    with codecs.open(os.path.join(HERE, *parts), 'r') as fp:
+        return fp.read()
+
+
+def find_version(*file_paths):
+    version_file = read(*file_paths)
+    version_match = re.search(r"^__version__ = ['\"]([^'\"]*)['\"]",
+                              version_file, re.M)
+    if version_match:
+        return version_match.group(1)
+    raise RuntimeError("Unable to find version string.")
+
+
+__name__ = 'kashgari-tf'
+__author__ = "BrikerMan"
+__copyright__ = "Copyright 2018, BrikerMan"
+__credits__ = []
+__license__ = "Apache License 2.0"
+__maintainer__ = "BrikerMan"
+__email__ = "[email protected]"
+
+__url__ = 'https://github.com/BrikerMan/Kashgari'
+__description__ = 'Simple, Keras-powered multilingual NLP framework,' \
+                  ' allows you to build your models in 5 minutes for named entity recognition (NER),' \
+                  ' part-of-speech tagging (PoS) and text classification tasks. ' \
+                  'Includes BERT, GPT-2 and word2vec embedding.'
+
+__version__ = '0.5.5'
+README = (HERE / "README.md").read_text(encoding='utf-8')
+
+with codecs.open('requirements.txt', 'r', 'utf8') as reader:
+    install_requires = list(map(lambda x: x.strip(), reader.readlines()))
+
+setup(
+    name=__name__,
+    version=__version__,
+    description=__description__,
+    python_requires='>3.6',
+    long_description=README,
+    long_description_content_type="text/markdown",
+    author=__author__,
+    author_email=__email__,
+    url=__url__,
+    packages=find_packages(exclude=('tests',)),
+    install_requires=install_requires,
+    include_package_data=True,
+    license=__license__,
+    classifiers=[
+        'License :: OSI Approved :: Apache Software License',
+        # 'Programming Language :: Python',
+        'Programming Language :: Python :: 3.6',
+        'Programming Language :: Python :: Implementation :: CPython',
+        'Programming Language :: Python :: Implementation :: PyPy'
+    ],
+)
+
+if __name__ == "__main__":
+    print("Hello world")