稀牛lesson1
python 基础
目录
- Python介绍
- 基本数据结构
- 变量和表达式
- 字符窜
- 列表
- 判定语句
- 循环语句
- 集合/set，元组/tuble，字典/dictionary
python 简介
- python R
- 一天内能写Python是有可能的
- 流行程度：深度学习，人工智能
深度学习
google：tensorflow
facebook：pytorch+caffe2
Amazone:mxnet
机器学习
scikit-learn numpy pandas xgboost/LightGBM
大数据
hadoop（map-reduce） JAVA spark scala
都是用Python去实现的
- 因为数据科学家，用数据驱动的方式去解决实际生活中的各种问题。但是，花了大量时间去coding
- 但理想的状况是，你把主要的精力放在分析数据，了解数据和解决问题本身上
1. 寻求帮助
- Python有内置的说明文档 help
- dir
import pandas as pd
# 数据科学的比赛，阿里，京东，会有比赛，其实可以多去参加的
help(pd)
Help on package pandas:
NAME
pandas
DESCRIPTION
pandas - a powerful data analysis and manipulation library for Python
=====================================================================
**pandas** is a Python package providing fast, flexible, and expressive data
structures designed to make working with "relational" or "labeled" data both
easy and intuitive. It aims to be the fundamental high-level building block for
doing practical, **real world** data analysis in Python. Additionally, it has
the broader goal of becoming **the most powerful and flexible open source data
analysis / manipulation tool available in any language**. It is already well on
its way toward this goal.
Main Features
-------------
Here are just a few of the things that pandas does well:
- Easy handling of missing data in floating point as well as non-floating
point data
- Size mutability: columns can be inserted and deleted from DataFrame and
higher dimensional objects
- Automatic and explicit data alignment: objects can be explicitly aligned
to a set of labels, or the user can simply ignore the labels and let
`Series`, `DataFrame`, etc. automatically align the data for you in
computations
- Powerful, flexible group by functionality to perform split-apply-combine
operations on data sets, for both aggregating and transforming data
- Make it easy to convert ragged, differently-indexed data in other Python
and NumPy data structures into DataFrame objects
- Intelligent label-based slicing, fancy indexing, and subsetting of large
data sets
- Intuitive merging and joining data sets
- Flexible reshaping and pivoting of data sets
- Hierarchical labeling of axes (possible to have multiple labels per tick)
- Robust IO tools for loading data from flat files (CSV and delimited),
Excel files, databases, and saving/loading data from the ultrafast HDF5
format
- Time series-specific functionality: date range generation and frequency
conversion, moving window statistics, moving window linear regressions,
date shifting and lagging, etc.
PACKAGE CONTENTS
_libs (package)
_version
api (package)
compat (package)
computation (package)
conftest
core (package)
errors (package)
formats (package)
io (package)
json
lib
parser
plotting (package)
stats (package)
testing
tests (package)
tools (package)
tseries (package)
tslib
types (package)
util (package)
SUBMODULES
_hashtable
_lib
_tslib
offsets
DATA
IndexSlice =
NaT = NaT
__docformat__ = 'restructuredtext'
datetools =
get_option =
json =
parser =
set_option =
tslib = import tensorflow as tf
help(tf)
Help on package tensorflow:
NAME
tensorflow
DESCRIPTION
# Copyright 2015 The TensorFlow Authors. All Rights Reserved.
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ==============================================================================
PACKAGE CONTENTS
contrib (package)
core (package)
examples (package)
python (package)
tensorboard (package)
tools (package)
SUBMODULES
app
compat
errors
estimator
flags
gfile
graph_util
image
layers
logging
losses
metrics
nn
python_io
pywrap_tensorflow
resource_loader
saved_model
sdca
sets
spectral
summary
sysconfig
test
train
user_ops
DATA
COMPILER_VERSION = '4.8.4'
GIT_VERSION = 'v1.1.0-rc0-61-g1ec6ed5'
GRAPH_DEF_VERSION = 21
GRAPH_DEF_VERSION_MIN_CONSUMER = 0
GRAPH_DEF_VERSION_MIN_PRODUCER = 0
QUANTIZED_DTYPES = frozenset({tf.qint8, tf.quint8, tf.qint32, tf.qint1...
VERSION = '1.1.0'
__compiler_version__ = '4.8.4'
__git_version__ = 'v1.1.0-rc0-61-g1ec6ed5'
bfloat16 = tf.bfloat16
bool = tf.bool
complex128 = tf.complex128
complex64 = tf.complex64
contrib =
double = tf.float64
float16 = tf.float16
float32 = tf.float32
float64 = tf.float64
half = tf.float16
int16 = tf.int16
int32 = tf.int32
int64 = tf.int64
int8 = tf.int8
newaxis = None
qint16 = tf.qint16
qint32 = tf.qint32
qint8 = tf.qint8
quint16 = tf.quint16
quint8 = tf.quint8
resource = tf.resource
string = tf.string
uint16 = tf.uint16
uint8 = tf.uint8
VERSION
1.1.0
FILE
/home/bog/anaconda3/lib/python3.6/site-packages/tensorflow/__init__.py
tab有自动补全功能 ，比如tf. 后面按一个tab键，他会把后面可以接上的函数列出来
import sklearn
dir(sklearn.clone)
['__annotations__',
'__call__',
'__class__',
'__closure__',
'__code__',
'__defaults__',
'__delattr__',
'__dict__',
'__dir__',
'__doc__',
'__eq__',
'__format__',
'__ge__',
'__get__',
'__getattribute__',
'__globals__',
'__gt__',
'__hash__',
'__init__',
'__init_subclass__',
'__kwdefaults__',
'__le__',
'__lt__',
'__module__',
'__name__',
'__ne__',
'__new__',
'__qualname__',
'__reduce__',
'__reduce_ex__',
'__repr__',
'__setattr__',
'__sizeof__',
'__str__',
'__subclasshook__']
dir(tf)
['AggregationMethod',
'Assert',
'AttrValue',
'COMPILER_VERSION',
'ConditionalAccumulator',
'ConditionalAccumulatorBase',
'ConfigProto',
'DType',
'DeviceSpec',
'Dimension',
'Event',
'FIFOQueue',
'FixedLenFeature',
'FixedLenSequenceFeature',
'FixedLengthRecordReader',
'GIT_VERSION',
'GPUOptions',
'GRAPH_DEF_VERSION',
'GRAPH_DEF_VERSION_MIN_CONSUMER',
'GRAPH_DEF_VERSION_MIN_PRODUCER',
'Graph',
'GraphDef',
'GraphKeys',
'GraphOptions',
'HistogramProto',
'IdentityReader',
'IndexedSlices',
'InteractiveSession',
'LogMessage',
'NameAttrList',
'NoGradient',
'NodeDef',
'NotDifferentiable',
'OpError',
'Operation',
'OptimizerOptions',
'PaddingFIFOQueue',
'Print',
'PriorityQueue',
'QUANTIZED_DTYPES',
'QueueBase',
'RandomShuffleQueue',
'ReaderBase',
'RegisterGradient',
'RunMetadata',
'RunOptions',
'Session',
'SessionLog',
'SparseConditionalAccumulator',
'SparseFeature',
'SparseTensor',
'SparseTensorValue',
'Summary',
'TFRecordReader',
'Tensor',
'TensorArray',
'TensorInfo',
'TensorShape',
'TextLineReader',
'VERSION',
'VarLenFeature',
'Variable',
'VariableScope',
'WholeFileReader',
'_LazyContribLoader',
'__builtins__',
'__cached__',
'__compiler_version__',
'__doc__',
'__file__',
'__git_version__',
'__loader__',
'__name__',
'__package__',
'__path__',
'__spec__',
'__version__',
'abs',
'accumulate_n',
'acos',
'add',
'add_check_numerics_ops',
'add_n',
'add_to_collection',
'all_variables',
'app',
'arg_max',
'arg_min',
'argmax',
'argmin',
'as_dtype',
'as_string',
'asin',
'assert_equal',
'assert_greater',
'assert_greater_equal',
'assert_integer',
'assert_less',
'assert_less_equal',
'assert_negative',
'assert_non_negative',
'assert_non_positive',
'assert_none_equal',
'assert_positive',
'assert_proper_iterable',
'assert_rank',
'assert_rank_at_least',
'assert_type',
'assert_variables_initialized',
'assign',
'assign_add',
'assign_sub',
'atan',
'batch_to_space',
'batch_to_space_nd',
'betainc',
'bfloat16',
'bincount',
'bitcast',
'bool',
'boolean_mask',
'broadcast_dynamic_shape',
'broadcast_static_shape',
'case',
'cast',
'ceil',
'check_numerics',
'cholesky',
'cholesky_solve',
'clip_by_average_norm',
'clip_by_global_norm',
'clip_by_norm',
'clip_by_value',
'compat',
'complex',
'complex128',
'complex64',
'concat',
'cond',
'confusion_matrix',
'conj',
'constant',
'constant_initializer',
'container',
'contrib',
'control_dependencies',
'convert_to_tensor',
'convert_to_tensor_or_indexed_slices',
'convert_to_tensor_or_sparse_tensor',
'cos',
'count_nonzero',
'count_up_to',
'create_partitioned_variables',
'cross',
'cumprod',
'cumsum',
'decode_base64',
'decode_csv',
'decode_json_example',
'decode_raw',
'delete_session_tensor',
'depth_to_space',
'dequantize',
'deserialize_many_sparse',
'device',
'diag',
'diag_part',
'digamma',
'div',
'divide',
'double',
'dynamic_partition',
'dynamic_stitch',
'edit_distance',
'einsum',
'encode_base64',
'equal',
'erf',
'erfc',
'errors',
'estimator',
'exp',
'expand_dims',
'expm1',
'extract_image_patches',
'eye',
'fake_quant_with_min_max_args',
'fake_quant_with_min_max_args_gradient',
'fake_quant_with_min_max_vars',
'fake_quant_with_min_max_vars_gradient',
'fake_quant_with_min_max_vars_per_channel',
'fake_quant_with_min_max_vars_per_channel_gradient',
'fft',
'fft2d',
'fft3d',
'fill',
'fixed_size_partitioner',
'flags',
'float16',
'float32',
'float64',
'floor',
'floor_div',
'floordiv',
'floormod',
'foldl',
'foldr',
'gather',
'gather_nd',
'get_collection',
'get_collection_ref',
'get_default_graph',
'get_default_session',
'get_local_variable',
'get_seed',
'get_session_handle',
'get_session_tensor',
'get_variable',
'get_variable_scope',
'gfile',
'global_norm',
'global_variables',
'global_variables_initializer',
'gradients',
'graph_util',
'greater',
'greater_equal',
'group',
'half',
'hessians',
'histogram_fixed_width',
'identity',
'ifft',
'ifft2d',
'ifft3d',
'igamma',
'igammac',
'imag',
'image',
'import_graph_def',
'initialize_all_tables',
'initialize_all_variables',
'initialize_local_variables',
'initialize_variables',
'int16',
'int32',
'int64',
'int8',
'invert_permutation',
'is_finite',
'is_inf',
'is_nan',
'is_non_decreasing',
'is_numeric_tensor',
'is_strictly_increasing',
'is_variable_initialized',
'layers',
'lbeta',
'less',
'less_equal',
'lgamma',
'lin_space',
'linspace',
'load_file_system_library',
'load_op_library',
'local_variables',
'local_variables_initializer',
'log',
'log1p',
'logging',
'logical_and',
'logical_not',
'logical_or',
'logical_xor',
'losses',
'make_template',
'map_fn',
'matching_files',
'matmul',
'matrix_band_part',
'matrix_determinant',
'matrix_diag',
'matrix_diag_part',
'matrix_inverse',
'matrix_set_diag',
'matrix_solve',
'matrix_solve_ls',
'matrix_transpose',
'matrix_triangular_solve',
'maximum',
'meshgrid',
'metrics',
'min_max_variable_partitioner',
'minimum',
'mod',
'model_variables',
'moving_average_variables',
'multinomial',
'multiply',
'name_scope',
'negative',
'newaxis',
'nn',
'no_op',
'no_regularizer',
'norm',
'not_equal',
'one_hot',
'ones',
'ones_initializer',
'ones_like',
'op_scope',
'orthogonal_initializer',
'pad',
'parallel_stack',
'parse_example',
'parse_single_example',
'parse_single_sequence_example',
'parse_tensor',
'placeholder',
'placeholder_with_default',
'polygamma',
'pow',
'py_func',
'python_io',
'pywrap_tensorflow',
'qint16',
'qint32',
'qint8',
'qr',
'quantize_v2',
'quantized_concat',
'quint16',
'quint8',
'random_crop',
'random_gamma',
'random_normal',
'random_normal_initializer',
'random_poisson',
'random_shuffle',
'random_uniform',
'random_uniform_initializer',
'range',
'rank',
'read_file',
'real',
'realdiv',
'reciprocal',
'reduce_all',
'reduce_any',
'reduce_join',
'reduce_logsumexp',
'reduce_max',
'reduce_mean',
'reduce_min',
'reduce_prod',
'reduce_sum',
'register_tensor_conversion_function',
'report_uninitialized_variables',
'required_space_to_batch_paddings',
'reset_default_graph',
'reshape',
'resource',
'resource_loader',
'reverse',
'reverse_sequence',
'reverse_v2',
'rint',
'round',
'rsqrt',
'saturate_cast',
'saved_model',
'scalar_mul',
'scan',
'scatter_add',
'scatter_div',
'scatter_mul',
'scatter_nd',
'scatter_nd_add',
'scatter_nd_sub',
'scatter_nd_update',
'scatter_sub',
'scatter_update',
'sdca',
'segment_max',
'segment_mean',
'segment_min',
'segment_prod',
'segment_sum',
'self_adjoint_eig',
'self_adjoint_eigvals',
'sequence_mask',
'serialize_many_sparse',
'serialize_sparse',
'set_random_seed',
'setdiff1d',
'sets',
'shape',
'shape_n',
'sigmoid',
'sign',
'sin',
'size',
'slice',
'space_to_batch',
'space_to_batch_nd',
'space_to_depth',
'sparse_add',
'sparse_concat',
'sparse_fill_empty_rows',
'sparse_mask',
'sparse_matmul',
'sparse_maximum',
'sparse_merge',
'sparse_minimum',
'sparse_placeholder',
'sparse_reduce_sum',
'sparse_reduce_sum_sparse',
'sparse_reorder',
'sparse_reset_shape',
'sparse_reshape',
'sparse_retain',
'sparse_segment_mean',
'sparse_segment_sqrt_n',
'sparse_segment_sum',
'sparse_softmax',
'sparse_split',
'sparse_tensor_dense_matmul',
'sparse_tensor_to_dense',
'sparse_to_dense',
'sparse_to_indicator',
'sparse_transpose',
'spectral',
'split',
'sqrt',
'square',
'squared_difference',
'squeeze',
'stack',
'stop_gradient',
'strided_slice',
'string',
'string_join',
'string_split',
'string_to_hash_bucket',
'string_to_hash_bucket_fast',
'string_to_hash_bucket_strong',
'string_to_number',
'substr',
'subtract',
'summary',
'svd',
'sysconfig',
'tables_initializer',
'tan',
'tanh',
'tensordot',
'test',
'tile',
'to_bfloat16',
'to_double',
'to_float',
'to_int32',
'to_int64',
'trace',
'train',
'trainable_variables',
'transpose',
'truediv',
'truncated_normal',
'truncated_normal_initializer',
'truncatediv',
'truncatemod',
'tuple',
'uint16',
'uint8',
'uniform_unit_scaling_initializer',
'unique',
'unique_with_counts',
'unsorted_segment_max',
'unsorted_segment_sum',
'unstack',
'user_ops',
'variable_axis_size_partitioner',
'variable_op_scope',
'variable_scope',
'variables_initializer',
'verify_tensor_all_finite',
'where',
'while_loop',
'write_file',
'zeros',
'zeros_initializer',
'zeros_like',
'zeta']
python的运算
- +/-/*//
6/4
1.5
6//4
1
4**0.5
2.0
4%3
1
python基本数据类型，变量，运算，表达式
3.变量
基本数据类型：
- int 整数
- float 浮点数
- str 字符窜
- bool型
- type（）
X = 12
type(X)
int
y = -5.32
type(y)
float
z = 'bog5d'
type(z)
str
z[:3]
'bog'
a ="bog\n5d"
print(a)
bog
5d
a1 = 'bog\n5d'
print(a1)
bog
5d
d = True
type(d)
bool
e = pd.DataFrame()
type(e)
pandas.core.frame.DataFrame
表达式
- Python 会用表达式
### 切片
a = 'bog5diloveyou'
a
'bog5diloveyou'
a[4]
'd'
a[-3]
'y'
a[1:4]
#第二位到第五位
#左闭右开，是切片原则
'og5'
a[-6:-2]
'ovey'
a[2:]
'g5diloveyou'
a[:5]
'bog5d'
字符窜函数
dir(str)
['__add__',
'__class__',
'__contains__',
'__delattr__',
'__dir__',
'__doc__',
'__eq__',
'__format__',
'__ge__',
'__getattribute__',
'__getitem__',
'__getnewargs__',
'__gt__',
'__hash__',
'__init__',
'__init_subclass__',
'__iter__',
'__le__',
'__len__',
'__lt__',
'__mod__',
'__mul__',
'__ne__',
'__new__',
'__reduce__',
'__reduce_ex__',
'__repr__',
'__rmod__',
'__rmul__',
'__setattr__',
'__sizeof__',
'__str__',
'__subclasshook__',
'capitalize',
'casefold',
'center',
'count',
'encode',
'endswith',
'expandtabs',
'find',
'format',
'format_map',
'index',
'isalnum',
'isalpha',
'isdecimal',
'isdigit',
'isidentifier',
'islower',
'isnumeric',
'isprintable',
'isspace',
'istitle',
'isupper',
'join',
'ljust',
'lower',
'lstrip',
'maketrans',
'partition',
'replace',
'rfind',
'rindex',
'rjust',
'rpartition',
'rsplit',
'rstrip',
'split',
'splitlines',
'startswith',
'strip',
'swapcase',
'title',
'translate',
'upper',
'zfill']
a.upper()
'BOG5DILOVEYOU'
a.endswith('u')
True
b= " "+a+"-yes!!!"
b
' bog5diloveyou-yes!!!'
b=b.strip()
c = "我 爱 达州"
c.split(" ")
['我', '爱', '达州']
b.find('5d')
3
list列表
list是Python中的数据结构，表示一连串的数据的集合（有序的）
names = ["bobi","eva","joe","二狗","李雷","hanmeimei"]
#元素是任何玩意儿，都可以
type(list)
type
type(names)
list
dir(list)
['__add__',
'__class__',
'__contains__',
'__delattr__',
'__delitem__',
'__dir__',
'__doc__',
'__eq__',
'__format__',
'__ge__',
'__getattribute__',
'__getitem__',
'__gt__',
'__hash__',
'__iadd__',
'__imul__',
'__init__',
'__init_subclass__',
'__iter__',
'__le__',
'__len__',
'__lt__',
'__mul__',
'__ne__',
'__new__',
'__reduce__',
'__reduce_ex__',
'__repr__',
'__reversed__',
'__rmul__',
'__setattr__',
'__setitem__',
'__sizeof__',
'__str__',
'__subclasshook__',
'append',
'clear',
'copy',
'count',
'extend',
'index',
'insert',
'pop',
'remove',
'reverse',
'sort']
len(names)
6
mixed = ['bobi',2,3.14,[1,2,34]]
len(mixed)
4
### 切片
mixed[1]
2
mixed[3]
[1, 2, 34]
mixed[3][2]
34
mixed[2:]
[3.14, [1, 2, 34]]
split<==>join(对一堆字符串组成的list去做的）
names
['bobi', 'eva', 'joe', '二狗', '李雷', 'hanmeimei']
mixed
['bobi', 2, 3.14, [1, 2, 34]]
" ## ".join(names)
'bobi ## eva ## joe ## 二狗 ## 李雷 ## hanmeimei'
"+".join(names)
'bobi+eva+joe+二狗+李雷+hanmeimei'
append(往尾巴上去追加)
mixed
['bobi', 2, 3.14, [1, 2, 34], '36', '36', '36']
mixed.extend([54,66,99])
mixed
['bobi', 2, 3.14, [1, 2, 34], '36', '36', '36', 54, 66, 99]
mixed.index('36')
4
mixed.pop()
99
mixed
['bobi', 2, 3.14, [1, 2, 34], '36', '36', '36', 54, 66]
流程控制
条件判断 if else
#判断一个老人
age = 25
if age>60:
print("一把老骨头啊")
elif age>35:
print("形状之年啊")
else:
print("小年轻")
小年轻
for name in names:
print(name)
bobi
eva
joe
二狗
李雷
hanmeimei
for i,name in enumerate(names):
print(i,name)
0 bobi
1 eva
2 joe
3 二狗
4 李雷
5 hanmeimei
i = 0
while i<10:
print(i)
i+=1
0
1
2
3
4
5
6
7
8
9
i = 0
while True:
print(i)
i+=1
if i>6:
break
0
1
2
3
4
5
6
i = 0
while True:
i+=1
if i%3== 0:
continue
print(i)
if i>6:
break
1
2
4
5
7
for name in names:
print('my name is'+name)
my name isbobi
my name iseva
my name isjoe
my name is二狗
my name is李雷
my name ishanmeimei
###列表推到式
['my name is '+name for name in names]
['my name is bobi',
'my name is eva',
'my name is joe',
'my name is 二狗',
'my name is 李雷',
'my name is hanmeimei']
num_list = list(range(1,16))
[num**2 for num in num_list]
[1, 4, 9, 16, 25, 36, 49, 64, 81, 100, 121, 144, 169, 196, 225]
[num**2 for num in num_list if num%2==1]
[1, 9, 25, 49, 81, 121, 169, 225]
[num**2 for num in num_list if (num%2==1 and num<5)]
[1, 9]
set/ 集合
num_list = num_list*2
num_list
[1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15,
1,
2,
3,
4,
5,
6,
7,
8,
9,
10,
11,
12,
13,
14,
15]
set(num_list)
{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15}
字典/dictionary
有时候，我们需要一下key—value这样的数据。键值对
legs ={'spider:8','pig:4','duck:2'}
legs.{'pig'}
File "", line 1
legs.{'pig'}
^
SyntaxError: invalid syntax
list(legs.key())
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
in ()
----> 1 list(legs.key())
AttributeError: 'set' object has no attribute 'key'
字典推到式
my_list = list(range(10))
my_list
[0, 1, 2, 3, 4, 5, 6, 7, 8, 9]
{num:num**3 for num in my_list}
{0: 0, 1: 1, 2: 8, 3: 27, 4: 64, 5: 125, 6: 216, 7: 343, 8: 512, 9: 729}
###高级排序
my_list = [5,1,4,2,3]
my_list.sort()#成员函数
my_list
[1, 2, 3, 4, 5]
tmp_list=[5,4,3,1,2]
sorted(tmp_list)#外部函数，不会改变数据序列本身
[1, 2, 3, 4, 5]
tmp_list
[5, 4, 3, 1, 2]
sorted(tmp_list,reverse=False)
[1, 2, 3, 4, 5]
strs =['ccc','aaaa','eeeeeee','kdjehd']
sorted(strs)
['aaaa', 'ccc', 'eeeeeee', 'kdjehd']
sorted(strs,key=len)#根据key对元素做处理后的结果排序
['ccc', 'aaaa', 'kdjehd', 'eeeeeee']
tmp_strs= ['aa','CC','BB','ZZ']
sorted(tmp_strs,key=str.lower)
['aa', 'BB', 'CC', 'ZZ']
函数
- def 关键字
- 括号包含参数列表
- 语句需要缩进
def my_sum(a,b):
return (a+b+1)**(1/3)
my_sum(3,4)
2.0
def fib(n):
a,b = 0,1
for i in range(n):
print(a,end=" ")
a,b=b,a+b
print()
fib(15)
0 1 1 2 3 5 8 13 21 34 55 89 144 233 377
def my_mul(x,y=3):
return x*y
my_mul(4,5)
20
my_mul(4)
12
文件的读写
!ls
2017-11-25 19-16-05屏幕截图.png 波哥linux创建的 文档 稀牛学院课1.ipynb
!2017-11-25\ 19-16-05屏幕截图.png
/bin/sh: 1: 2017-11-25 19-16-05屏幕截图.png: not found
!pwd
/home/bog/图片
help(open)
Help on built-in function open in module io:
open(file, mode='r', buffering=-1, encoding=None, errors=None, newline=None, closefd=True, opener=None)
Open file and return a stream. Raise IOError upon failure.
file is either a text or byte string giving the name (and the path
if the file isn't in the current working directory) of the file to
be opened or an integer file descriptor of the file to be
wrapped. (If a file descriptor is given, it is closed when the
returned I/O object is closed, unless closefd is set to False.)
mode is an optional string that specifies the mode in which the file
is opened. It defaults to 'r' which means open for reading in text
mode. Other common values are 'w' for writing (truncating the file if
it already exists), 'x' for creating and writing to a new file, and
'a' for appending (which on some Unix systems, means that all writes
append to the end of the file regardless of the current seek position).
In text mode, if encoding is not specified the encoding used is platform
dependent: locale.getpreferredencoding(False) is called to get the
current locale encoding. (For reading and writing raw bytes use binary
mode and leave encoding unspecified.) The available modes are:
========= ===============================================================
Character Meaning
--------- ---------------------------------------------------------------
'r' open for reading (default)
'w' open for writing, truncating the file first
'x' create a new file and open it for writing
'a' open for writing, appending to the end of the file if it exists
'b' binary mode
't' text mode (default)
'+' open a disk file for updating (reading and writing)
'U' universal newline mode (deprecated)
========= ===============================================================
The default mode is 'rt' (open for reading text). For binary random
access, the mode 'w+b' opens and truncates the file to 0 bytes, while
'r+b' opens the file without truncation. The 'x' mode implies 'w' and
raises an `FileExistsError` if the file already exists.
Python distinguishes between files opened in binary and text modes,
even when the underlying operating system doesn't. Files opened in
binary mode (appending 'b' to the mode argument) return contents as
bytes objects without any decoding. In text mode (the default, or when
't' is appended to the mode argument), the contents of the file are
returned as strings, the bytes having been first decoded using a
platform-dependent encoding or using the specified encoding if given.
'U' mode is deprecated and will raise an exception in future versions
of Python. It has no effect in Python 3. Use newline to control
universal newlines mode.
buffering is an optional integer used to set the buffering policy.
Pass 0 to switch buffering off (only allowed in binary mode), 1 to select
line buffering (only usable in text mode), and an integer > 1 to indicate
the size of a fixed-size chunk buffer. When no buffering argument is
given, the default buffering policy works as follows:
* Binary files are buffered in fixed-size chunks; the size of the buffer
is chosen using a heuristic trying to determine the underlying device's
"block size" and falling back on `io.DEFAULT_BUFFER_SIZE`.
On many systems, the buffer will typically be 4096 or 8192 bytes long.
* "Interactive" text files (files for which isatty() returns True)
use line buffering. Other text files use the policy described above
for binary files.
encoding is the name of the encoding used to decode or encode the
file. This should only be used in text mode. The default encoding is
platform dependent, but any encoding supported by Python can be
passed. See the codecs module for the list of supported encodings.
errors is an optional string that specifies how encoding errors are to
be handled---this argument should not be used in binary mode. Pass
'strict' to raise a ValueError exception if there is an encoding error
(the default of None has the same effect), or pass 'ignore' to ignore
errors. (Note that ignoring encoding errors can lead to data loss.)
See the documentation for codecs.register or run 'help(codecs.Codec)'
for a list of the permitted encoding error strings.
newline controls how universal newlines works (it only applies to text
mode). It can be None, '', '\n', '\r', and '\r\n'. It works as
follows:
* On input, if newline is None, universal newlines mode is
enabled. Lines in the input can end in '\n', '\r', or '\r\n', and
these are translated into '\n' before being returned to the
caller. If it is '', universal newline mode is enabled, but line
endings are returned to the caller untranslated. If it has any of
the other legal values, input lines are only terminated by the given
string, and the line ending is returned to the caller untranslated.
* On output, if newline is None, any '\n' characters written are
translated to the system default line separator, os.linesep. If
newline is '' or '\n', no translation takes place. If newline is any
of the other legal values, any '\n' characters written are translated
to the given string.
If closefd is False, the underlying file descriptor will be kept open
when the file is closed. This does not work when a file name is given
and must be True in that case.
A custom opener can be used by passing a callable as *opener*. The
underlying file descriptor for the file object is then obtained by
calling *opener* with (*file*, *flags*). *opener* must return an open
file descriptor (passing os.open as *opener* results in functionality
similar to passing None).
open() returns a file object whose type depends on the mode, and
through which the standard file operations such as reading and writing
are performed. When open() is used to open a file in a text mode ('w',
'r', 'wt', 'rt', etc.), it returns a TextIOWrapper. When used to open
a file in a binary mode, the returned class varies: in read binary
mode, it returns a BufferedReader; in write binary and append binary
modes, it returns a BufferedWriter, and in read/write mode, it returns
a BufferedRandom.
It is also possible to use a string or bytearray as a file for both
reading and writing. For strings StringIO can be used like a file
opened in a text mode, and for bytes a BytesIO can be used like a file
opened in a binary mode.
f = open('./无标题文档','r')
f.read()
"sorted(tmp_list)\ndsjfsjofdsfjsdajfdsa\nfjdsiojfds\n4\nkds'\n"
f.close()
f = open('./无标题文档','r')
f.readlines()
['sorted(tmp_list)\n',
'dsjfsjofdsfjsdajfdsa\n',
'fjdsiojfds\n',
'4\n',
"kds'\n"]
f.close()
for line in open('./无标题文档','r'):
print(len(line.strip()))
16
20
10
1
4
作业-统计词频
给你一个文件，统计这个文档中出现了的单词，出现的次数。
正则表达式
tem_str = "有谁喜欢郭金明的书，那么韩寒呢"
tem_str.find("郭金明")
4
匹配的是一个模式，我让你找到所有邮箱字符串
email_str = "my email is [email protected],his email is [email protected],goodbye"
import re #正则表达式
#\d 数字
# \2 字母，数字，下划线。。。。
#\s 所有的空格 空白 或者tab 换行
# + 贪婪匹配
# * 匹配0次或者若干次
match=re.search(r'[\w.-]+@[\w.-]+',email_str)
if match:
print(match.group())
[email protected]
[email protected]寒晓阳的邮箱
emails = re.findall(r'[\w.-]+@[\w.-]+',email_str)
if emails:
for email in emails:
print(email)
[email protected]
[email protected]