Skip to content

Commit 41a2b81

Browse files
eric496eric496
committed
add notebooks for each section
1 parent 8c3ceee commit 41a2b81

12 files changed

+5127
-503
lines changed

‎0. Data Type.ipynb

Lines changed: 303 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,303 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"metadata": {},
7+
"outputs": [],
8+
"source": [
9+
"import numpy as np"
10+
]
11+
},
12+
{
13+
"cell_type": "markdown",
14+
"metadata": {},
15+
"source": [
16+
"### A list of Numpy Data Types"
17+
]
18+
},
19+
{
20+
"cell_type": "code",
21+
"execution_count": 2,
22+
"metadata": {},
23+
"outputs": [
24+
{
25+
"data": {
26+
"text/html": [
27+
"<div>\n",
28+
"<style scoped>\n",
29+
" .dataframe tbody tr th:only-of-type {\n",
30+
" vertical-align: middle;\n",
31+
" }\n",
32+
"\n",
33+
" .dataframe tbody tr th {\n",
34+
" vertical-align: top;\n",
35+
" }\n",
36+
"\n",
37+
" .dataframe thead th {\n",
38+
" text-align: right;\n",
39+
" }\n",
40+
"</style>\n",
41+
"<table border=\"1\" class=\"dataframe\">\n",
42+
" <thead>\n",
43+
" <tr style=\"text-align: right;\">\n",
44+
" <th></th>\n",
45+
" <th>Type</th>\n",
46+
" <th>Type Code</th>\n",
47+
" </tr>\n",
48+
" </thead>\n",
49+
" <tbody>\n",
50+
" <tr>\n",
51+
" <th>0</th>\n",
52+
" <td>int8</td>\n",
53+
" <td>i1</td>\n",
54+
" </tr>\n",
55+
" <tr>\n",
56+
" <th>1</th>\n",
57+
" <td>uint8</td>\n",
58+
" <td>u1</td>\n",
59+
" </tr>\n",
60+
" <tr>\n",
61+
" <th>2</th>\n",
62+
" <td>int16</td>\n",
63+
" <td>i2</td>\n",
64+
" </tr>\n",
65+
" <tr>\n",
66+
" <th>3</th>\n",
67+
" <td>uint16</td>\n",
68+
" <td>u2</td>\n",
69+
" </tr>\n",
70+
" <tr>\n",
71+
" <th>4</th>\n",
72+
" <td>int32</td>\n",
73+
" <td>i4</td>\n",
74+
" </tr>\n",
75+
" <tr>\n",
76+
" <th>5</th>\n",
77+
" <td>uint32</td>\n",
78+
" <td>u4</td>\n",
79+
" </tr>\n",
80+
" <tr>\n",
81+
" <th>6</th>\n",
82+
" <td>int64</td>\n",
83+
" <td>i8</td>\n",
84+
" </tr>\n",
85+
" <tr>\n",
86+
" <th>7</th>\n",
87+
" <td>uint64</td>\n",
88+
" <td>u8</td>\n",
89+
" </tr>\n",
90+
" <tr>\n",
91+
" <th>8</th>\n",
92+
" <td>float16</td>\n",
93+
" <td>f2</td>\n",
94+
" </tr>\n",
95+
" <tr>\n",
96+
" <th>9</th>\n",
97+
" <td>float32</td>\n",
98+
" <td>f4 or f</td>\n",
99+
" </tr>\n",
100+
" <tr>\n",
101+
" <th>10</th>\n",
102+
" <td>float64</td>\n",
103+
" <td>f8 or d</td>\n",
104+
" </tr>\n",
105+
" <tr>\n",
106+
" <th>11</th>\n",
107+
" <td>float128</td>\n",
108+
" <td>f16 or g</td>\n",
109+
" </tr>\n",
110+
" <tr>\n",
111+
" <th>12</th>\n",
112+
" <td>complex64</td>\n",
113+
" <td>c8</td>\n",
114+
" </tr>\n",
115+
" <tr>\n",
116+
" <th>13</th>\n",
117+
" <td>complex128</td>\n",
118+
" <td>c16</td>\n",
119+
" </tr>\n",
120+
" <tr>\n",
121+
" <th>14</th>\n",
122+
" <td>bool</td>\n",
123+
" <td></td>\n",
124+
" </tr>\n",
125+
" <tr>\n",
126+
" <th>15</th>\n",
127+
" <td>object</td>\n",
128+
" <td>O</td>\n",
129+
" </tr>\n",
130+
" <tr>\n",
131+
" <th>16</th>\n",
132+
" <td>string_</td>\n",
133+
" <td>S</td>\n",
134+
" </tr>\n",
135+
" <tr>\n",
136+
" <th>17</th>\n",
137+
" <td>unicode_</td>\n",
138+
" <td>U</td>\n",
139+
" </tr>\n",
140+
" </tbody>\n",
141+
"</table>\n",
142+
"</div>"
143+
],
144+
"text/plain": [
145+
" Type Type Code\n",
146+
"0 int8 i1\n",
147+
"1 uint8 u1\n",
148+
"2 int16 i2\n",
149+
"3 uint16 u2\n",
150+
"4 int32 i4\n",
151+
"5 uint32 u4\n",
152+
"6 int64 i8\n",
153+
"7 uint64 u8\n",
154+
"8 float16 f2\n",
155+
"9 float32 f4 or f\n",
156+
"10 float64 f8 or d\n",
157+
"11 float128 f16 or g\n",
158+
"12 complex64 c8\n",
159+
"13 complex128 c16\n",
160+
"14 bool \n",
161+
"15 object O\n",
162+
"16 string_ S\n",
163+
"17 unicode_ U"
164+
]
165+
},
166+
"execution_count": 2,
167+
"metadata": {},
168+
"output_type": "execute_result"
169+
}
170+
],
171+
"source": [
172+
"import pandas as pd\n",
173+
"dtypes = pd.DataFrame(\n",
174+
" {\n",
175+
" 'Type': ['int8', 'uint8', 'int16', 'uint16', 'int32', 'uint32', 'int64', 'uint64', 'float16', 'float32', 'float64', 'float128', 'complex64', 'complex128', 'bool', 'object', 'string_', 'unicode_'],\n",
176+
" 'Type Code': ['i1', 'u1', 'i2', 'u2', 'i4', 'u4', 'i8', 'u8', 'f2', 'f4 or f', 'f8 or d', 'f16 or g', 'c8', 'c16', '', 'O', 'S', 'U']\n",
177+
" }\n",
178+
")\n",
179+
"\n",
180+
"dtypes"
181+
]
182+
},
183+
{
184+
"cell_type": "code",
185+
"execution_count": 3,
186+
"metadata": {},
187+
"outputs": [
188+
{
189+
"name": "stdout",
190+
"output_type": "stream",
191+
"text": [
192+
"[1. 2. 3.]\n",
193+
"float32\n",
194+
"[1.+2.j 3.-4.j]\n",
195+
"complex64\n",
196+
"[False True True]\n",
197+
"bool\n"
198+
]
199+
}
200+
],
201+
"source": [
202+
"# create an array with a specified data type\n",
203+
"arr = np.array([1,2,3], dtype='f4')\n",
204+
"print(arr)\n",
205+
"print(arr.dtype)\n",
206+
"\n",
207+
"arr = np.array([1+2j, 3-4j], dtype=np.complex64)\n",
208+
"print(arr)\n",
209+
"print(arr.dtype)\n",
210+
"\n",
211+
"arr = np.array([0, 1, 1], dtype=np.bool)\n",
212+
"print(arr)\n",
213+
"print(arr.dtype)"
214+
]
215+
},
216+
{
217+
"cell_type": "markdown",
218+
"metadata": {},
219+
"source": [
220+
"### string data type"
221+
]
222+
},
223+
{
224+
"cell_type": "code",
225+
"execution_count": 4,
226+
"metadata": {},
227+
"outputs": [
228+
{
229+
"name": "stdout",
230+
"output_type": "stream",
231+
"text": [
232+
"[b'abc' b'def']\n",
233+
"|S3\n"
234+
]
235+
}
236+
],
237+
"source": [
238+
"# set the max length of the string using S + some number, such as 'S3'\n",
239+
"# any string longer than the max length will be truncated\n",
240+
"s = np.array(['abc', 'defg'], dtype='S3')\n",
241+
"print(s)\n",
242+
"print(s.dtype)"
243+
]
244+
},
245+
{
246+
"cell_type": "code",
247+
"execution_count": 5,
248+
"metadata": {},
249+
"outputs": [
250+
{
251+
"name": "stdout",
252+
"output_type": "stream",
253+
"text": [
254+
"|S3\n",
255+
"<U3\n"
256+
]
257+
}
258+
],
259+
"source": [
260+
"# numpy string and unicode data types are fixed-length\n",
261+
"# string_ and unicode_ will treat the longest string in the array as the default length when creating an array\n",
262+
"arr = np.array(['a', 'ab', 'abc'], dtype=np.string_)\n",
263+
"print(arr.dtype)\n",
264+
"\n",
265+
"arr = np.array(['a', 'ab', 'abc'], dtype=np.unicode_)\n",
266+
"print(arr.dtype)"
267+
]
268+
},
269+
{
270+
"cell_type": "code",
271+
"execution_count": 6,
272+
"metadata": {},
273+
"outputs": [],
274+
"source": [
275+
"# what does the above \"|\" and \"<\" mean?\n",
276+
"# they are the byte order indicators, which is beyond the scope of this tutorial\n",
277+
"# you can check it out here: https://docs.scipy.org/doc/numpy/reference/generated/numpy.dtype.byteorder.html\n",
278+
"# and here: https://en.wikipedia.org/wiki/Endianness"
279+
]
280+
}
281+
],
282+
"metadata": {
283+
"kernelspec": {
284+
"display_name": "Python 3",
285+
"language": "python",
286+
"name": "python3"
287+
},
288+
"language_info": {
289+
"codemirror_mode": {
290+
"name": "ipython",
291+
"version": 3
292+
},
293+
"file_extension": ".py",
294+
"mimetype": "text/x-python",
295+
"name": "python",
296+
"nbconvert_exporter": "python",
297+
"pygments_lexer": "ipython3",
298+
"version": "3.6.6"
299+
}
300+
},
301+
"nbformat": 4,
302+
"nbformat_minor": 2
303+
}

0 commit comments

Comments
 (0)