In [9]:
import matplotlib.pyplot as plt
%matplotlib inline
import pandas as pd
import numpy as np
import scipy.stats as stats

Input the Data

In [5]:
df = pd.read_csv("/Users/hongyeliu/Desktop/CS361JupyterNotebook/Lecture1/mtcars.csv")
df
Out[5]:
Unnamed: 0 mpg cyl disp hp drat wt qsec vs am gear carb
0 Mazda RX4 21.0 6 160.0 110 3.90 2.620 16.46 0 1 4 4
1 Mazda RX4 Wag 21.0 6 160.0 110 3.90 2.875 17.02 0 1 4 4
2 Datsun 710 22.8 4 108.0 93 3.85 2.320 18.61 1 1 4 1
3 Hornet 4 Drive 21.4 6 258.0 110 3.08 3.215 19.44 1 0 3 1
4 Hornet Sportabout 18.7 8 360.0 175 3.15 3.440 17.02 0 0 3 2
5 Valiant 18.1 6 225.0 105 2.76 3.460 20.22 1 0 3 1
6 Duster 360 14.3 8 360.0 245 3.21 3.570 15.84 0 0 3 4
7 Merc 240D 24.4 4 146.7 62 3.69 3.190 20.00 1 0 4 2
8 Merc 230 22.8 4 140.8 95 3.92 3.150 22.90 1 0 4 2
9 Merc 280 19.2 6 167.6 123 3.92 3.440 18.30 1 0 4 4
10 Merc 280C 17.8 6 167.6 123 3.92 3.440 18.90 1 0 4 4
11 Merc 450SE 16.4 8 275.8 180 3.07 4.070 17.40 0 0 3 3
12 Merc 450SL 17.3 8 275.8 180 3.07 3.730 17.60 0 0 3 3
13 Merc 450SLC 15.2 8 275.8 180 3.07 3.780 18.00 0 0 3 3
14 Cadillac Fleetwood 10.4 8 472.0 205 2.93 5.250 17.98 0 0 3 4
15 Lincoln Continental 10.4 8 460.0 215 3.00 5.424 17.82 0 0 3 4
16 Chrysler Imperial 14.7 8 440.0 230 3.23 5.345 17.42 0 0 3 4
17 Fiat 128 32.4 4 78.7 66 4.08 2.200 19.47 1 1 4 1
18 Honda Civic 30.4 4 75.7 52 4.93 1.615 18.52 1 1 4 2
19 Toyota Corolla 33.9 4 71.1 65 4.22 1.835 19.90 1 1 4 1
20 Toyota Corona 21.5 4 120.1 97 3.70 2.465 20.01 1 0 3 1
21 Dodge Challenger 15.5 8 318.0 150 2.76 3.520 16.87 0 0 3 2
22 AMC Javelin 15.2 8 304.0 150 3.15 3.435 17.30 0 0 3 2
23 Camaro Z28 13.3 8 350.0 245 3.73 3.840 15.41 0 0 3 4
24 Pontiac Firebird 19.2 8 400.0 175 3.08 3.845 17.05 0 0 3 2
25 Fiat X1-9 27.3 4 79.0 66 4.08 1.935 18.90 1 1 4 1
26 Porsche 914-2 26.0 4 120.3 91 4.43 2.140 16.70 0 1 5 2
27 Lotus Europa 30.4 4 95.1 113 3.77 1.513 16.90 1 1 5 2
28 Ford Pantera L 15.8 8 351.0 264 4.22 3.170 14.50 0 1 5 4
29 Ferrari Dino 19.7 6 145.0 175 3.62 2.770 15.50 0 1 5 6
30 Maserati Bora 15.0 8 301.0 335 3.54 3.570 14.60 0 1 5 8
31 Volvo 142E 21.4 4 121.0 109 4.11 2.780 18.60 1 1 4 2

Bar chart

In [6]:
Num_cylinders = df["cyl"].value_counts()
Num_cylinders
Out[6]:
8    14
4    11
6     7
Name: cyl, dtype: int64
In [14]:
plt.bar(Num_cylinders.keys(), Num_cylinders,color=['black',  'blue', 'orange'])
plt.title("Count of cars by Cylinder")
plt.xlabel("Num. of Cylinder")
plt.ylabel("Count")
Out[14]:
Text(0, 0.5, 'Count')
In [ ]:

Histogram

Input the iris data set

In [12]:
df2 = pd.read_csv("/Users/hongyeliu/Desktop/CS361JupyterNotebook/Lecture1/iris.csv")
df2
Out[12]:
Unnamed: 0 Sepal.Length Sepal.Width Petal.Length Petal.Width Species
0 1 5.1 3.5 1.4 0.2 setosa
1 2 4.9 3.0 1.4 0.2 setosa
2 3 4.7 3.2 1.3 0.2 setosa
3 4 4.6 3.1 1.5 0.2 setosa
4 5 5.0 3.6 1.4 0.2 setosa
... ... ... ... ... ... ...
145 146 6.7 3.0 5.2 2.3 virginica
146 147 6.3 2.5 5.0 1.9 virginica
147 148 6.5 3.0 5.2 2.0 virginica
148 149 6.2 3.4 5.4 2.3 virginica
149 150 5.9 3.0 5.1 1.8 virginica

150 rows × 6 columns

In [15]:
plt.subplot(1, 2, 1)
plt.hist(df2["Sepal.Length"], bins=50)
plt.xlabel("Sepal Length")
plt.ylabel("Count")
plt.title("Histogram of Sepal length with 50 bins")
plt.subplot(1, 2, 2)
plt.hist(df2["Sepal.Length"], bins=20)
plt.xlabel("Sepal Length")
plt.ylabel("Count")
plt.title("Histogram of Sepal length with 20 bins")
plt.subplots_adjust(bottom=0, top=1, left=-0.5, right=1.5)

Conditional Histogrom

In [58]:
n_bins = 20

tmpdf1 = df2[df2["Species"]=="setosa"]
tmpdf2 = df2[df2["Species"]=="versicolor"]
tmpdf3 = df2[df2["Species"]=="virginica"]


colors = ['orange', 'blue', 'black']
labels = ['setosa','versicolor','virginica']
x_multi = [tmpdf1["Sepal.Length"],tmpdf2["Sepal.Length"],tmpdf3["Sepal.Length"]]
plt.hist(x_multi, n_bins, histtype='bar',color=colors,label= labels)
plt.legend(prop={'size': 10})
plt.xlabel("Sepal Length")
plt.ylabel("Count")
Out[58]:
Text(0, 0.5, 'Count')

Input the CS361 student score (Homeworks + project + exams) data set

df3 = pd.read_csv("/Users/hongyeliu/Desktop/CS361JupyterNotebook/Lecture1/Data_finalAna.csv") df3 = df3.iloc[:,3:10] df3 df_4 = df3[["Total_HWPRJExam","ParticipationScore"]] df_4

In [79]:
n_bins = 10

tmpdf1 = df_4[df_4["ParticipationScore"]==1]
tmpdf2 = df_4[df_4["ParticipationScore"]==0]


colors = ['orange', 'blue']
labels = ['Full','NotFull']
x_multi = [tmpdf1["Total_HWPRJExam"],tmpdf2["Total_HWPRJExam"]]
plt.hist(x_multi, n_bins, histtype='bar',color=colors,label= labels)
plt.legend(prop={'size': 10})
plt.xlabel("Score")
plt.ylabel("Count")
plt.savefig('Score_FullOrNot.png')

Calculate the mean score of the students who have full participation and that of students who don't.

In [90]:
m1 = tmpdf1["Total_HWPRJExam"].mean()
m1
print("Mean:", m1)
s1 = tmpdf1["Total_HWPRJExam"].std(ddof=0)
print("Standard deviation:", s1)

Mean: 889.9936936936937
Standard deviation: 81.60863348524836
In [91]:
m2 = tmpdf2["Total_HWPRJExam"].mean()
m2
print("Mean:", m2)
s2 = tmpdf2["Total_HWPRJExam"].std(ddof=0)
print("Standard deviation:", s2)

Mean: 760.1778378378378
Standard deviation: 146.9616497158934

Calculate the median score of the students who have full participation and that of students who don't.

In [83]:
md1 = tmpdf1["Total_HWPRJExam"].median()
md1
Out[83]:
909.4
In [84]:
md2 = tmpdf2["Total_HWPRJExam"].median()
md2
Out[84]:
802.0
In [ ]: