Mean car prices#

Creating a visualization that displays the mean price of each car manufacturer of the automobiles dataset.

Importing libraries and packages#

 1# Warnings
 2import warnings
 3
 4# Mathematical operations and data manipulation
 5import pandas as pd
 6
 7# Visualisation
 8from bokeh.plotting import figure, show
 9from bokeh.models import LinearColorMapper
10
11# Output
12from bokeh.io import output_notebook
13
14output_notebook()
15warnings.filterwarnings("ignore")
Loading BokehJS ...

Set paths#

1# Path to datasets directory
2data_path = "./datasets"
3# Path to assets directory (for saving results to)
4assets_path = "./assets"

Loading dataset#

1dataset = pd.read_csv(f"{data_path}/automobiles.csv")

Exploring dataset#

1# Shape of the dataset
2print("Shape of the dataset: ", dataset.shape)
3# Head
4dataset.head()

Shape of the dataset:  (201, 14)
make fuel-type num-of-doors body-style engine-location length width height num-of-cylinders horsepower peak-rpm city-mpg highway-mpg price
0 alfa-romero gas two convertible front 168.8 64.1 48.8 four 111 5000 21 27 13495
1 alfa-romero gas two convertible front 168.8 64.1 48.8 four 111 5000 21 27 16500
2 alfa-romero gas two hatchback front 171.2 65.5 52.4 six 154 5000 19 26 16500
3 audi gas four sedan front 176.6 66.2 54.3 four 102 5500 24 30 13950
4 audi gas four sedan front 176.6 66.4 54.3 five 115 5500 18 22 17450

Preprocessing#

1# Adding a new column with the indices called index
2dataset["index"] = dataset.index

Visualisation#

1# plotting a point for each car with its price
2plot = figure(
3    title="Car prices", x_axis_label="Car Index", y_axis_label="Price"
4)
5plot.scatter(dataset["index"], dataset["price"])
6
7show(plot)

1# Grouping the dataset by the make column and aggregating it by the mean
2grouped_average = dataset.groupby(["make"], as_index=False).mean()
3grouped_average
make length width height city-mpg highway-mpg price index
0 alfa-romero 169.600000 64.566667 50.000000 20.333333 26.666667 15498.333333 1.0
1 audi 184.766667 68.850000 54.833333 19.333333 24.500000 17859.166667 5.5
2 bmw 184.500000 66.475000 54.825000 19.375000 25.375000 26118.750000 12.5
3 chevrolet 151.933333 62.500000 52.400000 41.000000 46.333333 6007.000000 18.0
4 dodge 160.988889 64.166667 51.644444 28.000000 34.111111 7875.444444 24.0
5 honda 160.769231 64.384615 53.238462 30.384615 35.461538 8184.692308 35.0
6 isuzu 171.650000 63.500000 52.450000 24.000000 29.000000 8916.500000 42.5
7 jaguar 196.966667 69.933333 51.133333 14.333333 18.333333 34600.000000 45.0
8 mazda 170.805882 65.588235 53.358824 25.705882 31.941176 10652.882353 55.0
9 mercedes-benz 195.262500 71.062500 55.725000 18.500000 21.000000 33647.000000 67.5
10 mercury 178.400000 68.000000 54.800000 19.000000 24.000000 16503.000000 72.0
11 mitsubishi 168.030769 65.253846 50.692308 24.923077 31.153846 9239.769231 79.0
12 nissan 170.988889 65.088889 53.633333 27.000000 32.944444 10415.666667 94.5
13 peugot 191.136364 68.390909 57.181818 22.454545 26.636364 15489.090909 109.0
14 plymouth 164.900000 64.271429 51.971429 28.142857 34.142857 7963.428571 118.0
15 porsche 168.900000 65.825000 51.250000 17.500000 25.500000 31400.500000 123.5
16 renault 179.150000 66.550000 52.850000 23.000000 31.000000 9595.000000 126.5
17 saab 186.600000 66.500000 56.100000 20.333333 27.333333 15223.333333 130.5
18 subaru 168.858333 64.950000 53.750000 26.333333 30.750000 8541.250000 139.5
19 toyota 171.934375 65.090625 53.721875 27.500000 32.906250 9885.812500 161.5
20 volkswagen 172.533333 65.616667 55.183333 28.583333 34.916667 10077.500000 183.5
21 volvo 188.800000 67.963636 56.236364 21.181818 25.818182 18063.181818 195.0 
 1# Plotting the manufacturers and their mean car prices
 2grouped_plot = figure(
 3    title="Car Manufacturer Mean Prices",
 4    x_axis_label="Car Manufacturer",
 5    y_axis_label="Mean Price",
 6    x_range=grouped_average["make"],
 7)
 8grouped_plot.scatter(grouped_average["make"], grouped_average["price"])
 9
10show(grouped_plot)

1# Assigning the x label orientation the value of vertical
2grouped_plot.xaxis.major_label_orientation = "vertical"
3
4show(grouped_plot)

 1# Adding color based on the mean price to our elements
 2
 3color_mapper = LinearColorMapper(
 4    palette="Magma256",
 5    low=min(grouped_average["price"]),
 6    high=max(grouped_average["price"]),
 7)
 8
 9grouped_colored_plot = figure(
10    title="Car Manufacturer Mean Prices",
11    x_axis_label="Car Manufacturer",
12    y_axis_label="Mean Price",
13    x_range=grouped_average["make"],
14)
15grouped_colored_plot.scatter(
16    grouped_average["make"],
17    grouped_average["price"],
18    color={"field": "y", "transform": color_mapper},
19    size=15,
20)
21
22grouped_colored_plot.xaxis.major_label_orientation = "vertical"
23
24show(grouped_colored_plot)