Skip to content

Commit af3c3de

Browse files
mrankitguptamrankitgupta
authored
Files Upload
1 parent ad832ad commit af3c3de

12 files changed

+13702
-0
lines changed

Diff for: ‎Exercises - Week 1 to 6 of Statistics for Data Science with Python/1. Introduction_to_probability_distribution.ipynb

+643
Large diffs are not rendered by default.

Diff for: ‎Exercises - Week 1 to 6 of Statistics for Data Science with Python/2. Visualizing_Data.ipynb

+1,679
Large diffs are not rendered by default.

Diff for: ‎Exercises - Week 1 to 6 of Statistics for Data Science with Python/3. Descriptive_Stats.ipynb

+1,597
Large diffs are not rendered by default.

Diff for: ‎Exercises - Week 1 to 6 of Statistics for Data Science with Python/4. Regression_Analysis.ipynb

+1,544
Large diffs are not rendered by default.

Diff for: ‎Exercises - Week 1 to 6 of Statistics for Data Science with Python/5. Hypothesis_Testing.ipynb

+1,304
Large diffs are not rendered by default.

Diff for: ‎Exercises - Week 1 to 6 of Statistics for Data Science with Python/6. Statistics for Data Science with Python.ipynb

+325
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,325 @@
1+
{
2+
"cells": [
3+
{
4+
"cell_type": "code",
5+
"execution_count": 1,
6+
"metadata": {},
7+
"outputs": [],
8+
"source": [
9+
"import numpy as np\n",
10+
"import pandas as pd\n",
11+
"import matplotlib.pyplot as plt\n",
12+
"import seaborn as sns\n",
13+
"\n",
14+
"%matplotlib inline"
15+
]
16+
},
17+
{
18+
"cell_type": "markdown",
19+
"metadata": {},
20+
"source": [
21+
"### Introduction and Descriptive Statistics"
22+
]
23+
},
24+
{
25+
"cell_type": "code",
26+
"execution_count": 2,
27+
"metadata": {},
28+
"outputs": [],
29+
"source": [
30+
"x = [1, 3, 3, 4, 5, 6, 6, 7, 8, 8]"
31+
]
32+
},
33+
{
34+
"cell_type": "code",
35+
"execution_count": 3,
36+
"metadata": {},
37+
"outputs": [],
38+
"source": [
39+
"X = pd.DataFrame(x)"
40+
]
41+
},
42+
{
43+
"cell_type": "code",
44+
"execution_count": 4,
45+
"metadata": {},
46+
"outputs": [
47+
{
48+
"data": {
49+
"text/html": [
50+
"<div>\n",
51+
"<style scoped>\n",
52+
" .dataframe tbody tr th:only-of-type {\n",
53+
" vertical-align: middle;\n",
54+
" }\n",
55+
"\n",
56+
" .dataframe tbody tr th {\n",
57+
" vertical-align: top;\n",
58+
" }\n",
59+
"\n",
60+
" .dataframe thead th {\n",
61+
" text-align: right;\n",
62+
" }\n",
63+
"</style>\n",
64+
"<table border=\"1\" class=\"dataframe\">\n",
65+
" <thead>\n",
66+
" <tr style=\"text-align: right;\">\n",
67+
" <th></th>\n",
68+
" <th>0</th>\n",
69+
" </tr>\n",
70+
" </thead>\n",
71+
" <tbody>\n",
72+
" <tr>\n",
73+
" <th>count</th>\n",
74+
" <td>10.000000</td>\n",
75+
" </tr>\n",
76+
" <tr>\n",
77+
" <th>mean</th>\n",
78+
" <td>5.100000</td>\n",
79+
" </tr>\n",
80+
" <tr>\n",
81+
" <th>std</th>\n",
82+
" <td>2.330951</td>\n",
83+
" </tr>\n",
84+
" <tr>\n",
85+
" <th>min</th>\n",
86+
" <td>1.000000</td>\n",
87+
" </tr>\n",
88+
" <tr>\n",
89+
" <th>25%</th>\n",
90+
" <td>3.250000</td>\n",
91+
" </tr>\n",
92+
" <tr>\n",
93+
" <th>50%</th>\n",
94+
" <td>5.500000</td>\n",
95+
" </tr>\n",
96+
" <tr>\n",
97+
" <th>75%</th>\n",
98+
" <td>6.750000</td>\n",
99+
" </tr>\n",
100+
" <tr>\n",
101+
" <th>max</th>\n",
102+
" <td>8.000000</td>\n",
103+
" </tr>\n",
104+
" </tbody>\n",
105+
"</table>\n",
106+
"</div>"
107+
],
108+
"text/plain": [
109+
" 0\n",
110+
"count 10.000000\n",
111+
"mean 5.100000\n",
112+
"std 2.330951\n",
113+
"min 1.000000\n",
114+
"25% 3.250000\n",
115+
"50% 5.500000\n",
116+
"75% 6.750000\n",
117+
"max 8.000000"
118+
]
119+
},
120+
"execution_count": 4,
121+
"metadata": {},
122+
"output_type": "execute_result"
123+
}
124+
],
125+
"source": [
126+
"X.describe()"
127+
]
128+
},
129+
{
130+
"cell_type": "markdown",
131+
"metadata": {},
132+
"source": [
133+
"### Introduction to Probability Distribution"
134+
]
135+
},
136+
{
137+
"cell_type": "code",
138+
"execution_count": 5,
139+
"metadata": {},
140+
"outputs": [
141+
{
142+
"name": "stdout",
143+
"output_type": "stream",
144+
"text": [
145+
"180.0\n"
146+
]
147+
}
148+
],
149+
"source": [
150+
"Z = 1.50\n",
151+
"m = 150\n",
152+
"sigma = 20\n",
153+
"\n",
154+
"x = Z*sigma + m\n",
155+
"print(x)"
156+
]
157+
},
158+
{
159+
"cell_type": "code",
160+
"execution_count": 6,
161+
"metadata": {},
162+
"outputs": [
163+
{
164+
"name": "stdout",
165+
"output_type": "stream",
166+
"text": [
167+
"117.7\n"
168+
]
169+
}
170+
],
171+
"source": [
172+
"Z = -2.4\n",
173+
"m = 134.5\n",
174+
"sigma = 7.0\n",
175+
"\n",
176+
"y = Z*sigma + m\n",
177+
"print(y)"
178+
]
179+
},
180+
{
181+
"cell_type": "markdown",
182+
"metadata": {},
183+
"source": [
184+
"### Hypothesis Testing"
185+
]
186+
},
187+
{
188+
"cell_type": "code",
189+
"execution_count": 7,
190+
"metadata": {},
191+
"outputs": [
192+
{
193+
"data": {
194+
"text/plain": [
195+
"(463, 19)"
196+
]
197+
},
198+
"execution_count": 7,
199+
"metadata": {},
200+
"output_type": "execute_result"
201+
}
202+
],
203+
"source": [
204+
"df = pd.read_csv(\"teachingratings.csv\")\n",
205+
"df.shape"
206+
]
207+
},
208+
{
209+
"cell_type": "code",
210+
"execution_count": 8,
211+
"metadata": {},
212+
"outputs": [
213+
{
214+
"name": "stdout",
215+
"output_type": "stream",
216+
"text": [
217+
"7884\n"
218+
]
219+
}
220+
],
221+
"source": [
222+
"r = 439\n",
223+
"c = 19\n",
224+
"DF = (r-1)*(c-1)\n",
225+
"print(DF)"
226+
]
227+
},
228+
{
229+
"cell_type": "code",
230+
"execution_count": 9,
231+
"metadata": {},
232+
"outputs": [
233+
{
234+
"name": "stdout",
235+
"output_type": "stream",
236+
"text": [
237+
"2.1371514694800307\n"
238+
]
239+
}
240+
],
241+
"source": [
242+
"x = 91.54\n",
243+
"m = 63.18\n",
244+
"sigma = 13.27\n",
245+
"\n",
246+
"Z = (x-m)/sigma\n",
247+
"print(Z)"
248+
]
249+
},
250+
{
251+
"cell_type": "code",
252+
"execution_count": 10,
253+
"metadata": {},
254+
"outputs": [
255+
{
256+
"name": "stdout",
257+
"output_type": "stream",
258+
"text": [
259+
"76.6\n"
260+
]
261+
}
262+
],
263+
"source": [
264+
"#From Z table for probability of 0.25 = -0.67\n",
265+
"\n",
266+
"Z = -0.67\n",
267+
"m = 90\n",
268+
"sigma = 20\n",
269+
"\n",
270+
"time = Z*sigma + m\n",
271+
"print(time)"
272+
]
273+
},
274+
{
275+
"cell_type": "code",
276+
"execution_count": 11,
277+
"metadata": {},
278+
"outputs": [
279+
{
280+
"name": "stdout",
281+
"output_type": "stream",
282+
"text": [
283+
"3.000000000000002\n"
284+
]
285+
}
286+
],
287+
"source": [
288+
"x = 6.90\n",
289+
"mu = 5.85\n",
290+
"sd = 0.35\n",
291+
"\n",
292+
"Z = (x-mu)/sd\n",
293+
"print(Z)"
294+
]
295+
},
296+
{
297+
"cell_type": "code",
298+
"execution_count": null,
299+
"metadata": {},
300+
"outputs": [],
301+
"source": []
302+
}
303+
],
304+
"metadata": {
305+
"kernelspec": {
306+
"display_name": "Python 3",
307+
"language": "python",
308+
"name": "python3"
309+
},
310+
"language_info": {
311+
"codemirror_mode": {
312+
"name": "ipython",
313+
"version": 3
314+
},
315+
"file_extension": ".py",
316+
"mimetype": "text/x-python",
317+
"name": "python",
318+
"nbconvert_exporter": "python",
319+
"pygments_lexer": "ipython3",
320+
"version": "3.8.3"
321+
}
322+
},
323+
"nbformat": 4,
324+
"nbformat_minor": 4
325+
}

0 commit comments

Comments
 (0)