Initial commit

.gitignore

+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+pip-wheel-metadata/
+share/python-wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+MANIFEST
+
+# PyInstaller
+#  Usually these files are written by a python script from a template
+#  before PyInstaller builds the exe, so as to inject date/other infos into it.
+*.manifest
+*.spec
+
+# Installer logs
+pip-log.txt
+pip-delete-this-directory.txt
+
+# Unit test / coverage reports
+htmlcov/
+.tox/
+.nox/
+.coverage
+.coverage.*
+.cache
+nosetests.xml
+coverage.xml
+*.cover
+*.py,cover
+.hypothesis/
+.pytest_cache/
+cover/
+
+# Translations
+*.mo
+*.pot
+
+# Django stuff:
+*.log
+local_settings.py
+db.sqlite3
+db.sqlite3-journal
+
+# Flask stuff:
+instance/
+.webassets-cache
+
+# Scrapy stuff:
+.scrapy
+
+# Sphinx documentation
+docs/_build/
+
+# PyBuilder
+target/
+
+# Jupyter Notebook
+.ipynb_checkpoints
+
+# IPython
+profile_default/
+ipython_config.py
+
+# pyenv
+#   For a library or package, you might want to ignore these files since the code is
+#   intended to run in multiple environments; otherwise, check them in:
+# .python-version
+
+# pipenv
+#   According to pypa/pipenv#598, it is recommended to include Pipfile.lock in version control.
+#   However, in case of collaboration, if having platform-specific dependencies or dependencies
+#   having no cross-platform support, pipenv may install dependencies that don't work, or not
+#   install all needed dependencies.
+#Pipfile.lock
+
+# PEP 582; used by e.g. github.com/David-OConnor/pyflow
+__pypackages__/
+
+# Celery stuff
+celerybeat-schedule
+celerybeat.pid
+
+# SageMath parsed files
+*.sage.py
+
+# Environments
+.env
+.venv
+env/
+venv/
+ENV/
+env.bak/
+venv.bak/
+
+# Spyder project settings
+.spyderproject
+.spyproject
+
+# Rope project settings
+.ropeproject
+
+# mkdocs documentation
+/site
+
+# mypy
+.mypy_cache/
+.dmypy.json
+dmypy.json
+
+# Pyre type checker
+.pyre/
+
+# pytype static type analyzer
+.pytype/
\ No newline at end of file

01. novel-word-frequency/README.md

+# 小说词频统计
+
+> 统计 THE TRAGEDY OF ROMEO AND JULIET （罗密欧与朱丽叶）英文小说中各单词出现的次数。
+
+
+
+小说TXT文件下载链接：
+
+链接：https://pan.baidu.com/s/1u2c7O-617MboXSwBHnoOcA 提取码：vX47 
+
+
+
+评价标准：
+
+1、能正确打开源代码文件并可运行，2分
+
+2、正确分解出单词列表，如
+
+['THE', 'TRAGEDY', 'OF', 'ROMEO', 'AND', 'JULIET', 'by', 'William', 'Shakespeare']， 2分
+
+3、正确得到单词频次字典，如 {'straight;': 1, 'noise.': 1}， 4分
+
+4、按单词频次逆序输出结果，如 
+
+(601, 'the'), (549, 'I'), (468, 'and'), (451, 'to'),      2分
+
+
+
+以上为基本要求，作业不设标准答案，欢迎学员作业做进一步考虑，请说明自己的考虑方便批改人给分
+
+
+

01. novel-word-frequency/guo.py

+# coding=utf-8
+import functools
+
+file_path = 'English.txt'
+
+
+def sentence_to_words(word_list: list, sentence):
+    # 排除空行
+    sentence = sentence.strip()
+    if sentence:
+        word_list.extend(word for word in
+                         # 按空格作切分
+                         sentence.split()
+                         # 只取仅由字母组成的字符串
+                         if word.isalpha())
+    return word_list
+
+
+def analyze_frequencies(word_list: list):
+    frequencies = dict()
+    for word in word_list:
+        if word in frequencies:
+            # 如果之前遇到过，数量+1
+            frequencies[word] += 1
+        else:
+            # 如果之前没遇到过，这次遇到了，次数+1
+            frequencies[word] = 1
+    return frequencies
+
+
+def print_frequencies(frequencies):
+    print(
+        # 用逗号将列表拼接成一个大的字符串
+        ', '.join(
+            # 转换为 (频率, 单词) 的元组，然后转换为字符串表示
+            repr((times, word))
+            for word, times in
+            sorted(frequencies.items(),
+                   # 按第二个，频率，排序
+                   key=lambda pair: pair[1],
+                   # 递减顺序
+                   reverse=True
+                   )))
+
+
+with open(file_path, 'r', encoding='gb18030') as file_reader:
+    word_list = functools.reduce(sentence_to_words, file_reader, [])
+    # 正确分解出单词列表
+    # print(word_list)
+
+frequencies = analyze_frequencies(word_list)
+
+# print(frequencies)
+
+print_frequencies(frequencies)
\ No newline at end of file

01. novel-word-frequency/main.py

+# -*- coding: utf-8 -*-
+
+import os
+
+with open('English.txt') as file:
+    str = file.read().lower()
+
+words = []
+index = 0
+start = 0
+while index < len(str):
+    start = index
+    while str[index] != " " and str[index] not in ['.', ',', ':', '?', '!', '\n', '\u3000', '[', ']', '-', '(', ')', ';', '\"']:
+        index += 1
+        if index == len(str):
+            break
+    words.append(str[start:index])
+    if index == len(str):
+        break
+    while str[index] == " " or str[index] in ['.', ',', ':', '?', '!', '\n', '\u3000', '[', ']', '-', '(', ')', ';', '\"']:
+        index += 1
+        if index == len(str):
+            break
+
+# Now you can print the result by using
+# print(words)
+
+setword = set(words)
+dic = {}
+for i in setword:
+    count = words.count(i)
+    dic[i] = count
+
+# Now you can print the result by using
+# print(dic)
+
+# Or just import collections
+# then use print(collections.Counter(words))
+
+print(sorted(dic.items(), key=lambda count: count[1], reverse=True))

02. linear-regression-with-one-variable/README.md

+# 通过生成人工数据集合，基于TensorFlow实现y=3.1234*x+2.98线性回归
+
+通过上传附件方式提交 notebook文件（.ipynb）
+
+
+
+评分标准：
+
+1、生成 x_data，值为 [0, 100]之间500个等差数列数据集合作为样本特征
+
+根据目标线性方程 y=3.1234*x+2.98，生成相应的标签集合 y_data，1分；
+
+2、画出随机生成数据的散点图和想要通过学习得到的目标线性函数 y=3.1234*x+2.98，1分；
+
+3、构建回归模型，3分；
+
+4、训练模型，10轮，每训练20个样本显示损失值，2分；
+
+5、通过训练出的模型预测 x=5.79 时 y 的值，并显示根据目标方程显示的 y 值，1分；
+
+6、
+
+通过Tensorboard显示构建的计算图。
+
+上传的源代码中有相应的源代码
+
+结果计算图截图可以嵌入上交的notebook文件（.ipynb）
+
+嵌入图片的方法为markdown cell中代码 `<img src= "你的计算图文件名.png">`，2分。
+
+
+
+备注：如果不是上传notebook文件（.ipynb），可以用以下方案替代：
+
+1、源代码 .py 文件
+
+2、写一个说明文档，贴上散点图和计算图的图形，格式可以是word或者pdf
+
+3、以上两个文件通过压缩文件打包为一个zip或者rar文件
+
+
+
+强烈建议提交 notebook文件（.ipynb）（打包为压缩文件后上传）
+

03. predicting-boston-house-price/README.md

+# 波士顿房价预测线性回归实践
+
+按课程案例，动手完成编码实践。
+
+通过梯度下降优化器进行优化，尝试采用不同的学习率和训练轮数等超参数，记录训练后的损失值和W、b变量值。
+
+提交要求：
+
+1、至少5次不同超参数的运行结果的记录文档（word格式或者txt格式）
+
+2、你认为最优的一次带运行结果的源代码文件（.ipynb 格式）
+
+3、以上两个文件一起压缩为一个压缩文件后作为附件上传
+
+
+
+评价标准：
+
+1、完成案例中的代码，有完整的代码，模型能运行优化出结果，8分；
+
+2、调整过超参数，记录文件中有至少5组数据，2分；
\ No newline at end of file

LICENSE

+            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
+                    Version 2, December 2004
+
+ Copyright (C) 2004 Sam Hocevar <sam@hocevar.net>
+
+ Everyone is permitted to copy and distribute verbatim or modified
+ copies of this license document, and changing it is allowed as long
+ as the name is changed.
+
+            DO WHAT THE FUCK YOU WANT TO PUBLIC LICENSE
+   TERMS AND CONDITIONS FOR COPYING, DISTRIBUTION AND MODIFICATION
+
+  0. You just DO WHAT THE FUCK YOU WANT TO.

README.md

+# 深度学习应用开发-TensorFlow实践
+
+课程作业
+
+## License
+
+WTFPL
\ No newline at end of file