Skip to content

Commit 3709d51

Browse files
LeoBoraiLeoBorai
committed
feat: add exercises 2 and 3
1 parent 04cab06 commit 3709d51

File tree

4 files changed

+433
-0
lines changed

4 files changed

+433
-0
lines changed

‎Justfile‎

Lines changed: 3 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,3 +1,6 @@
1+
default:
2+
just --list
3+
14
dev:
25
docker compose up notebook
36

‎notebooks/chapter02_improved_photo_tag_analysis.ipynb‎ renamed to ‎notebooks/ex01_improved_photo_tag_analysis.ipynb‎

File renamed without changes.

‎notebooks/ex02_numpy_statistical_functions.ipynb‎

Lines changed: 175 additions & 0 deletions
Large diffs are not rendered by default.

‎notebooks/ex03_combine_three_series.ipynb‎

Lines changed: 255 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,255 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"id": "f9b79835-51ef-4edc-86f7-047e36526942",
7+
"metadata": {},
8+
"outputs": [
9+
{
10+
"name": "stdout",
11+
"output_type": "stream",
12+
"text": [
13+
"0 Jeff Russell\n",
14+
"1 Jane Boorman\n",
15+
"2 Tom Heints\n",
16+
"dtype: object\n"
17+
]
18+
}
19+
],
20+
"source": [
21+
"import pandas as pd\n",
22+
"\n",
23+
"data = ['Jeff Russell', 'Jane Boorman', 'Tom Heints']\n",
24+
"emps_names = pd.Series(data)\n",
25+
"\n",
26+
"print(emps_names)"
27+
]
28+
},
29+
{
30+
"cell_type": "code",
31+
"execution_count": 3,
32+
"id": "8b19bad6-f907-4881-835f-eeb1425f1e3f",
33+
"metadata": {},
34+
"outputs": [
35+
{
36+
"name": "stdout",
37+
"output_type": "stream",
38+
"text": [
39+
"9001 Jeff Russell\n",
40+
"9002 Jane Boorman\n",
41+
"9003 Tom Heints\n",
42+
"dtype: object\n"
43+
]
44+
}
45+
],
46+
"source": [
47+
"# Use custom indexes for series\n",
48+
"emps_names = pd.Series(data, index=[9001, 9002, 9003])\n",
49+
"print(emps_names)"
50+
]
51+
},
52+
{
53+
"cell_type": "code",
54+
"execution_count": 4,
55+
"id": "18fd7336-3676-46f3-ba68-d2a3314cba75",
56+
"metadata": {},
57+
"outputs": [
58+
{
59+
"name": "stdout",
60+
"output_type": "stream",
61+
"text": [
62+
"Jeff Russell\n"
63+
]
64+
}
65+
],
66+
"source": [
67+
"# Access by Series Index\n",
68+
"emp_9001 = emps_names[9001]\n",
69+
"print(emp_9001)"
70+
]
71+
},
72+
{
73+
"cell_type": "code",
74+
"execution_count": 5,
75+
"id": "0335b0df-fca2-4a36-8101-e8b8144abaa1",
76+
"metadata": {},
77+
"outputs": [
78+
{
79+
"name": "stdout",
80+
"output_type": "stream",
81+
"text": [
82+
"Jeff Russell\n"
83+
]
84+
}
85+
],
86+
"source": [
87+
"# Access by Index\n",
88+
"emp_idx_0 = emps_names.iloc[0]\n",
89+
"print(emp_idx_0)"
90+
]
91+
},
92+
{
93+
"cell_type": "code",
94+
"execution_count": 7,
95+
"id": "09bc2f12-91a8-42f5-9b1b-be30e0c47d31",
96+
"metadata": {},
97+
"outputs": [
98+
{
99+
"name": "stdout",
100+
"output_type": "stream",
101+
"text": [
102+
"9001 jeff.russel@company.com\n",
103+
"9002 jane.boorman@company.com\n",
104+
"9003 tom.heints@company.com\n",
105+
"dtype: object\n"
106+
]
107+
}
108+
],
109+
"source": [
110+
"emails = ['jeff.russel@company.com', 'jane.boorman@company.com', 'tom.heints@company.com']\n",
111+
"emps_emails = pd.Series(emails, index=[9001, 9002, 9003])\n",
112+
"\n",
113+
"print(emps_emails)"
114+
]
115+
},
116+
{
117+
"cell_type": "code",
118+
"execution_count": 8,
119+
"id": "6437eb50-155e-41ec-8913-3772e027ac7b",
120+
"metadata": {},
121+
"outputs": [
122+
{
123+
"name": "stdout",
124+
"output_type": "stream",
125+
"text": [
126+
" name email\n",
127+
"9001 Jeff Russell jeff.russel@company.com\n",
128+
"9002 Jane Boorman jane.boorman@company.com\n",
129+
"9003 Tom Heints tom.heints@company.com\n"
130+
]
131+
}
132+
],
133+
"source": [
134+
"# Merge 2 Series into 1 turning both into a single Data Frame\n",
135+
"# Set a name for the existing series\n",
136+
"emps_names.name = 'name'\n",
137+
"emps_emails.name = 'email'\n",
138+
"\n",
139+
"# Concatenate using columns with `axis = 1`\n",
140+
"df = pd.concat([emps_names, emps_emails], axis = 1)\n",
141+
"\n",
142+
"print(df)"
143+
]
144+
},
145+
{
146+
"cell_type": "markdown",
147+
"id": "d77b56b9-5dd4-4338-be39-5f5fe11e5bc2",
148+
"metadata": {},
149+
"source": [
150+
"Create a three/four column DataFrame"
151+
]
152+
},
153+
{
154+
"cell_type": "code",
155+
"execution_count": 11,
156+
"id": "b64f2b29-734c-4563-98ce-5e0e6453ce35",
157+
"metadata": {},
158+
"outputs": [
159+
{
160+
"name": "stdout",
161+
"output_type": "stream",
162+
"text": [
163+
"9001 +0 (982) 3454-8290\n",
164+
"9002 +0 (982) 1167-9388\n",
165+
"9003 +0 (982) 4544-8822\n",
166+
"Name: phone, dtype: object\n"
167+
]
168+
}
169+
],
170+
"source": [
171+
"phones = ['+0 (982) 3454-8290', '+0 (982) 1167-9388', '+0 (982) 4544-8822']\n",
172+
"\n",
173+
"emps_phones = pd.Series(phones, index=[9001, 9002, 9003])\n",
174+
"emps_phones.name = 'phone'\n",
175+
"\n",
176+
"print(emps_phones)"
177+
]
178+
},
179+
{
180+
"cell_type": "code",
181+
"execution_count": 12,
182+
"id": "9c539e29-0c9d-49dc-a061-00822e409efe",
183+
"metadata": {},
184+
"outputs": [
185+
{
186+
"name": "stdout",
187+
"output_type": "stream",
188+
"text": [
189+
"9001 Amsterdam\n",
190+
"9002 Budapest\n",
191+
"9003 Washington D.C.\n",
192+
"Name: location, dtype: object\n"
193+
]
194+
}
195+
],
196+
"source": [
197+
"locations = ['Amsterdam', 'Budapest', 'Washington D.C.']\n",
198+
"\n",
199+
"emps_locations = pd.Series(locations, index=[9001, 9002, 9003])\n",
200+
"emps_locations.name = 'location'\n",
201+
"\n",
202+
"print(emps_locations)"
203+
]
204+
},
205+
{
206+
"cell_type": "code",
207+
"execution_count": 14,
208+
"id": "9da839b8-2fcf-46b2-941b-1689d76b7f8a",
209+
"metadata": {},
210+
"outputs": [
211+
{
212+
"name": "stdout",
213+
"output_type": "stream",
214+
"text": [
215+
" name email phone \\\n",
216+
"9001 Jeff Russell jeff.russel@company.com +0 (982) 3454-8290 \n",
217+
"9002 Jane Boorman jane.boorman@company.com +0 (982) 1167-9388 \n",
218+
"9003 Tom Heints tom.heints@company.com +0 (982) 4544-8822 \n",
219+
"\n",
220+
" location \n",
221+
"9001 Amsterdam \n",
222+
"9002 Budapest \n",
223+
"9003 Washington D.C. \n"
224+
]
225+
}
226+
],
227+
"source": [
228+
"df = pd.concat([emps_names, emps_emails, emps_phones, emps_locations], axis = 1)\n",
229+
"\n",
230+
"print(df)"
231+
]
232+
}
233+
],
234+
"metadata": {
235+
"kernelspec": {
236+
"display_name": "Python 3 (ipykernel)",
237+
"language": "python",
238+
"name": "python3"
239+
},
240+
"language_info": {
241+
"codemirror_mode": {
242+
"name": "ipython",
243+
"version": 3
244+
},
245+
"file_extension": ".py",
246+
"mimetype": "text/x-python",
247+
"name": "python",
248+
"nbconvert_exporter": "python",
249+
"pygments_lexer": "ipython3",
250+
"version": "3.9.17"
251+
}
252+
},
253+
"nbformat": 4,
254+
"nbformat_minor": 5
255+
}

0 commit comments

Comments
 (0)