!pip install seaborn==0.11.0
Collecting seaborn==0.11.0
Downloading seaborn-0.11.0-py3-none-any.whl (283 kB)
|████████████████████████████████| 283 kB 15.1 MB/s
Requirement already satisfied: scipy>=1.0 in /opt/venv/lib/python3.7/site-packages (from seaborn==0.11.0) (1.5.4)
Requirement already satisfied: pandas>=0.23 in /opt/venv/lib/python3.7/site-packages (from seaborn==0.11.0) (1.0.5)
Requirement already satisfied: matplotlib>=2.2 in /opt/venv/lib/python3.7/site-packages (from seaborn==0.11.0) (3.3.2)
Requirement already satisfied: numpy>=1.15 in /opt/venv/lib/python3.7/site-packages (from seaborn==0.11.0) (1.19.4)
Requirement already satisfied: python-dateutil>=2.6.1 in /opt/venv/lib/python3.7/site-packages (from pandas>=0.23->seaborn==0.11.0) (2.8.1)
Requirement already satisfied: pytz>=2017.2 in /opt/venv/lib/python3.7/site-packages (from pandas>=0.23->seaborn==0.11.0) (2020.4)
Requirement already satisfied: cycler>=0.10 in /opt/venv/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn==0.11.0) (0.10.0)
Requirement already satisfied: certifi>=2020.06.20 in /opt/venv/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn==0.11.0) (2020.6.20)
Requirement already satisfied: pillow>=6.2.0 in /opt/venv/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn==0.11.0) (8.0.1)
Requirement already satisfied: pyparsing!=2.0.4,!=2.1.2,!=2.1.6,>=2.0.3 in /opt/venv/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn==0.11.0) (2.4.7)
Requirement already satisfied: kiwisolver>=1.0.1 in /opt/venv/lib/python3.7/site-packages (from matplotlib>=2.2->seaborn==0.11.0) (1.3.1)
Requirement already satisfied: six>=1.5 in /opt/venv/lib/python3.7/site-packages (from python-dateutil>=2.6.1->pandas>=0.23->seaborn==0.11.0) (1.15.0)
Installing collected packages: seaborn
Successfully installed seaborn-0.11.0
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import seaborn as sn
def load_dataset(path):
dataset = pd.read_csv(path, header=0, delimiter=',')
return dataset
train_dataset = load_dataset("train.csv")
test_dataset = load_dataset('test.csv')
x_train = train_dataset.drop("price_range", axis="columns").to_numpy()
y_train = train_dataset["price_range"].to_numpy()
train_dataset
| battery_powerint64501 – 1998 | blueint640 – 1 | clock_speedfloat640.5 – 3 | dual_simint640 – 1 | fcint640 – 19 | four_gint640 – 1 | int_memoryint642 – 64 | m_depfloat640.1 – 1 | mobile_wtint6480 – 200 | n_coresint641 – 8 | pcint640 – 20 | px_heightint640 – 1960 | px_widthint64500 – 1998 | ramint64256 – 3998 | sc_hint645 – 19 | sc_wint640 – 18 | talk_timeint642 – 20 | three_gint640 – 1 | touch_screenint640 – 1 | wifiint640 – 1 | price_rangeint640 – 3 | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 842 | 0 | 2.2 | 0 | 1 | 0 | 7 | 0.6 | 188 | 2 | 2 | 20 | 756 | 2549 | 9 | 7 | 19 | 0 | 0 | 1 | 1 | |
1 | 1021 | 1 | 0.5 | 1 | 0 | 1 | 53 | 0.7 | 136 | 3 | 6 | 905 | 1988 | 2631 | 17 | 3 | 7 | 1 | 1 | 0 | 2 | |
2 | 563 | 1 | 0.5 | 1 | 2 | 1 | 41 | 0.9 | 145 | 5 | 6 | 1263 | 1716 | 2603 | 11 | 2 | 9 | 1 | 1 | 0 | 2 | |
3 | 615 | 1 | 2.5 | 0 | 0 | 0 | 10 | 0.8 | 131 | 6 | 9 | 1216 | 1786 | 2769 | 16 | 8 | 11 | 1 | 0 | 0 | 2 | |
4 | 1821 | 1 | 1.2 | 0 | 13 | 1 | 44 | 0.6 | 141 | 2 | 14 | 1208 | 1212 | 1411 | 8 | 2 | 15 | 1 | 1 | 0 | 1 | |
| Expand rows 5 - 1994 | ||||||||||||||||||||||
1995 | 794 | 1 | 0.5 | 1 | 0 | 1 | 2 | 0.8 | 106 | 6 | 14 | 1222 | 1890 | 668 | 13 | 4 | 19 | 1 | 1 | 0 | 0 | |
1996 | 1965 | 1 | 2.6 | 1 | 0 | 0 | 39 | 0.2 | 187 | 4 | 3 | 915 | 1965 | 2032 | 11 | 10 | 16 | 1 | 1 | 1 | 2 | |
1997 | 1911 | 0 | 0.9 | 1 | 1 | 1 | 36 | 0.7 | 108 | 8 | 3 | 868 | 1632 | 3057 | 9 | 1 | 5 | 1 | 1 | 0 | 3 | |
1998 | 1512 | 0 | 0.9 | 0 | 4 | 1 | 46 | 0.1 | 145 | 5 | 5 | 336 | 670 | 869 | 18 | 10 | 19 | 1 | 1 | 1 | 0 | |
1999 | 510 | 1 | 2 | 1 | 5 | 1 | 45 | 0.9 | 168 | 6 | 16 | 483 | 754 | 3919 | 19 | 4 | 2 | 1 | 1 | 1 | 3 | |
| 2000 rows × 21 columns | ||||||||||||||||||||||
test_dataset
| idint641 – 1000 | battery_powerint64500 – 1999 | blueint640 – 1 | clock_speedfloat640.5 – 3 | dual_simint640 – 1 | fcint640 – 19 | four_gint640 – 1 | int_memoryint642 – 64 | m_depfloat640.1 – 1 | mobile_wtint6480 – 200 | n_coresint641 – 8 | pcint640 – 20 | px_heightint640 – 1907 | px_widthint64501 – 1998 | ramint64263 – 3989 | sc_hint645 – 19 | sc_wint640 – 18 | talk_timeint642 – 20 | three_gint640 – 1 | touch_screenint640 – 1 | wifiint640 – 1 | ||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0 | 1 | 1043 | 1 | 1.8 | 1 | 14 | 0 | 5 | 0.1 | 193 | 3 | 16 | 226 | 1412 | 3476 | 12 | 7 | 2 | 0 | 1 | 0 | |
1 | 2 | 841 | 1 | 0.5 | 1 | 4 | 1 | 61 | 0.8 | 191 | 5 | 12 | 746 | 857 | 3895 | 6 | 0 | 7 | 1 | 0 | 0 | |
2 | 3 | 1807 | 1 | 2.8 | 0 | 1 | 0 | 27 | 0.9 | 186 | 3 | 4 | 1270 | 1366 | 2396 | 17 | 10 | 10 | 0 | 1 | 1 | |
3 | 4 | 1546 | 0 | 0.5 | 1 | 18 | 1 | 25 | 0.5 | 96 | 8 | 20 | 295 | 1752 | 3893 | 10 | 0 | 7 | 1 | 1 | 0 | |
4 | 5 | 1434 | 0 | 1.4 | 0 | 11 | 1 | 49 | 0.5 | 108 | 6 | 18 | 749 | 810 | 1773 | 15 | 8 | 7 | 1 | 0 | 1 | |
| Expand rows 5 - 994 | ||||||||||||||||||||||
995 | 996 | 1700 | 1 | 1.9 | 0 | 0 | 1 | 54 | 0.5 | 170 | 7 | 17 | 644 | 913 | 2121 | 14 | 8 | 15 | 1 | 1 | 0 | |
996 | 997 | 609 | 0 | 1.8 | 1 | 0 | 0 | 13 | 0.9 | 186 | 4 | 2 | 1152 | 1632 | 1933 | 8 | 1 | 19 | 0 | 1 | 1 | |
997 | 998 | 1185 | 0 | 1.4 | 0 | 1 | 1 | 8 | 0.5 | 80 | 1 | 12 | 477 | 825 | 1223 | 5 | 0 | 14 | 1 | 0 | 0 | |
998 | 999 | 1533 | 1 | 0.5 | 1 | 0 | 0 | 50 | 0.4 | 171 | 2 | 12 | 38 | 832 | 2509 | 15 | 11 | 6 | 0 | 1 | 0 | |
999 | 1000 | 1270 | 1 | 0.5 | 0 | 4 | 1 | 35 | 0.1 | 140 | 6 | 19 | 457 | 608 | 2828 | 9 | 2 | 3 | 1 | 0 | 1 | |
| 1000 rows × 21 columns | ||||||||||||||||||||||
for i,j in zip(train_dataset.columns,train_dataset.dtypes):
print(i,":",j)
print("Number of attributes = %d" %train_dataset.columns.size)
battery_power : int64
blue : int64
clock_speed : float64
dual_sim : int64
fc : int64
four_g : int64
int_memory : int64
m_dep : float64
mobile_wt : int64
n_cores : int64
pc : int64
px_height : int64
px_width : int64
ram : int64
sc_h : int64
sc_w : int64
talk_time : int64
three_g : int64
touch_screen : int64
wifi : int64
price_range : int64
Number of attributes = 21
corrMatrix = train_dataset.corr()
sn.heatmap(corrMatrix, annot=True)
plt.show()