人工智能学习——第四课：Tensorflow学习——梯度下降算法优化（打印Tensorflow版本、打印数据集、生成线形图）

一、案例：线性回归实验

# 导入Tensorflow模块定义别名tf
import tensorflow as tf

# 打印Tensorflow版本
print (tf.__version__)
2.19.0

问题：存在无法找到文件

方法1（推荐使用原始字符串）：

data = pd.read_csv(r'D:\workspaces\Miniconda_workSpaces\datasheets\1.csv')

方法2（使用双反斜杠，特别注意最后一部分）：

data = pd.read_csv('D:\\workspaces\\Miniconda_workSpaces\\datasheets\\1.csv')

方法3（使用正斜杠）：

data = pd.read_csv('D:/workspaces/Miniconda_workSpaces/datasheets/1.csv')

# 第一次导入数据集文件income.csv
# 报错：数据文件income.csv导入数据集报utf-8编码错误
# 报错信息：“UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 0: invalid continuation byte”

# 第一次导入数据集
data = pd.read_csv('./income.csv')

# 详细报错
---------------------------------------------------------------------------
UnicodeDecodeError                        Traceback (most recent call last)
Cell In[8], line 1
----> 1 data = pd.read_csv('./income.csv')

File D:\Softwares\miniconda3\envs\Tensorflow\lib\site-packages\pandas\io\parsers\readers.py:1026, in read_csv(filepath_or_buffer, sep, delimiter, header, names, index_col, usecols, dtype, engine, converters, true_values, false_values, skipinitialspace, skiprows, skipfooter, nrows, na_values, keep_default_na, na_filter, verbose, skip_blank_lines, parse_dates, infer_datetime_format, keep_date_col, date_parser, date_format, dayfirst, cache_dates, iterator, chunksize, compression, thousands, decimal, lineterminator, quotechar, quoting, doublequote, escapechar, comment, encoding, encoding_errors, dialect, on_bad_lines, delim_whitespace, low_memory, memory_map, float_precision, storage_options, dtype_backend)
   1013 kwds_defaults = _refine_defaults_read(
   1014     dialect,
   1015     delimiter,
   (...)
   1022     dtype_backend=dtype_backend,
   1023 )
   1024 kwds.update(kwds_defaults)
-> 1026 return _read(filepath_or_buffer, kwds)

File D:\Softwares\miniconda3\envs\Tensorflow\lib\site-packages\pandas\io\parsers\readers.py:620, in _read(filepath_or_buffer, kwds)
    617 _validate_names(kwds.get("names", None))
    619 # Create the parser.
--> 620 parser = TextFileReader(filepath_or_buffer, **kwds)
    622 if chunksize or iterator:
    623     return parser

File D:\Softwares\miniconda3\envs\Tensorflow\lib\site-packages\pandas\io\parsers\readers.py:1620, in TextFileReader.__init__(self, f, engine, **kwds)
   1617     self.options["has_index_names"] = kwds["has_index_names"]
   1619 self.handles: IOHandles | None = None
-> 1620 self._engine = self._make_engine(f, self.engine)

File D:\Softwares\miniconda3\envs\Tensorflow\lib\site-packages\pandas\io\parsers\readers.py:1898, in TextFileReader._make_engine(self, f, engine)
   1895     raise ValueError(msg)
   1897 try:
-> 1898     return mapping[engine](f, **self.options)
   1899 except Exception:
   1900     if self.handles is not None:

File D:\Softwares\miniconda3\envs\Tensorflow\lib\site-packages\pandas\io\parsers\c_parser_wrapper.py:93, in CParserWrapper.__init__(self, src, **kwds)
     90 if kwds["dtype_backend"] == "pyarrow":
     91     # Fail here loudly instead of in cython after reading
     92     import_optional_dependency("pyarrow")
---> 93 self._reader = parsers.TextReader(src, **kwds)
     95 self.unnamed_cols = self._reader.unnamed_cols
     97 # error: Cannot determine type of 'names'

File parsers.pyx:574, in pandas._libs.parsers.TextReader.__cinit__()

File parsers.pyx:663, in pandas._libs.parsers.TextReader._get_header()

File parsers.pyx:874, in pandas._libs.parsers.TextReader._tokenize_rows()

File parsers.pyx:891, in pandas._libs.parsers.TextReader._check_tokenize_status()

File parsers.pyx:2053, in pandas._libs.parsers.raise_parser_error()

UnicodeDecodeError: 'utf-8' codec can't decode byte 0xd0 in position 0: invalid continuation byte

# 第二次导数数据文件incom.csv
# 报错：没有导入pandas模块定义pd别名
# 报错信息：“NameError: name 'pd' is not defined”
# 解决办法：添加编码格式
 
# 第二次导入数据文件 
data = pd.read_csv('./income.csv', encoding='gbk')

# 详细报错

---------------------------------------------------------------------------
NameError                                 Traceback (most recent call last)
Cell In[1], line 1
----> 1 data = pd.read_csv('./income.csv', encoding='gbk')

NameError: name 'pd' is not defined

# 第三次导入数据文件incom.csv
# 数据集更新
 
# 第三次导入数据文件，定义原数据gbk编码格式
data = pd.read_csv('./income.csv', encoding='gbk')
# 输出数据表
data
# 输出结果
    number    name    education            income
0    1        张三        20            10000
1    2        李四        12            9000
2    3        王五        34            8000
3    4        魏斌        16            12000
4    5        王红        23            10000
5    6        小新        24            10700
6    7        小玲        25            11000
7    8        小明        26            11300
8    9        小白        27            11600
9    10        小微        28            11900

# 定义x轴参数education列值
# 定义y轴参数income列值
plt.scatter(data.education, data.income)

# 输出绘图结果：

<matplotlib.collections.PathCollection at 0x2cc83e7f640>

 

# 总结
定义x轴（表education列值）与y轴（表income列值）的线性关系，后续整理f(x)=ax+b的函数关系及优化方法。