Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
Scribd
Upload
27 views

Bitcoine Data Analysis

machine learning project

Uploaded by

Rekha
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
27 views

Bitcoine Data Analysis

machine learning project

Uploaded by

Rekha
Copyright
© © All Rights Reserved
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 7

import pandas as pd

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
data={
'Date':pd.date_range(start='2023-01-01', periods=30, freq='D'),
'Open':np.random.uniform(15000,20000,30),
'High':np.random.uniform(20000,25000,30),
'Low': np.random.uniform(14000, 19000, 30),
'Close': np.random.uniform(15000, 25000, 30),
'Volume': np.random.uniform(500000, 1000000, 30),
'Market Cap': np.random.uniform(300000000, 600000000, 30)
}
df=pd.DataFrame(data)
print(df.head())

Date Open High Low


Close \
0 2023-01-01 16144.243872 23171.761891 16900.713506 18684.604178

1 2023-01-02 18755.360360 22617.447493 15975.580817 16365.262378

2 2023-01-03 15607.716807 21013.870519 17368.341532 24002.368427

3 2023-01-04 17434.177937 23694.117724 14097.496436 20665.980478

4 2023-01-05 17005.642760 23666.866543 15561.966208 21404.929413

Volume Market Cap


0 537502.686119 4.162288e+08
1 547545.825420 4.982122e+08
2 501945.592851 3.435210e+08
3 570856.577069 4.260933e+08
4 784086.534267 3.939071e+08

#ADD DATA
#performing EDA

print(df.describe())

Date Open High


Low \
count 30 30.000000 30.000000 30.000000

mean 2023-01-15 12:00:00 17053.789409 22544.547212 16475.514056

min 2023-01-01 00:00:00 15036.057382 20137.746621 14097.496436

25% 2023-01-08 06:00:00 16145.208605 21259.381735 15271.537415


50% 2023-01-15 12:00:00 16993.974271 22873.947872 16666.868915

75% 2023-01-22 18:00:00 17736.826400 23573.178068 17330.531382

max 2023-01-30 00:00:00 19796.237447 24950.390256 18960.212715

std NaN 1317.654355 1415.291285 1378.717402

Close Volume Market Cap


count 30.000000 30.000000 3.000000e+01
mean 20217.947782 726100.167418 4.483675e+08
min 15125.677998 501945.592851 3.003021e+08
25% 17567.860838 588814.008733 3.813930e+08
50% 20565.627597 710822.636409 4.525261e+08
75% 22611.556418 879452.881849 5.147255e+08
max 24958.580987 970019.423516 5.990765e+08
std 3150.148161 144289.080042 8.434337e+07

plt.figure(figsize=(10,6))
plt.plot(df['Date'], df['Close'], marker='o')
plt.title('Bitcoin Close Price Over Time')
plt.xlabel('Date')
plt.ylabel('Close Price')
plt.grid(True)
plt.show()
plt.figure(figsize=(8, 6))
sns.histplot(df['Volume'], kde=True)
plt.title('Distribution of Trading Volume')
plt.xlabel('Volume')
plt.ylabel('Frequency')
plt.show()

#creating a pair plot


sns.pairplot(df[['Open', 'Close', 'High', 'Low']])
plt.show()
#correlation
correlation_matrix = df[['Open', 'High', 'Low', 'Close',
'Volume']].corr()
plt.figure(figsize=(8, 6))
sns.heatmap(correlation_matrix, annot=True, cmap='coolwarm', vmin=-1,
vmax=1)
plt.title('Correlation Matrix')
plt.show()
#Apply Filtering Conditions
avg_volume = df['Volume'].mean()
df_filtered = df[(df['Close'] > df['Open']) & (df['Volume'] >
avg_volume)]
print(df_filtered)

Date Open High Low Close


\
4 2023-01-05 17005.642760 23666.866543 15561.966208 21404.929413

5 2023-01-06 16798.332183 24704.766766 15079.494912 19672.714263

6 2023-01-07 18191.610288 23235.830564 17777.650381 23336.592394

9 2023-01-10 15622.710262 22224.329570 15256.304438 21872.542150

10 2023-01-11 19462.332526 20706.147364 17449.254864 24453.685320

12 2023-01-13 16250.347302 24950.390256 18927.476239 22531.650917


14 2023-01-15 19796.237447 23786.024648 18330.797687 21313.114311

15 2023-01-16 17652.524327 20137.746621 16293.608392 24610.047470

16 2023-01-17 15036.057382 22983.248793 17097.104930 24881.993283

20 2023-01-21 17594.590039 21371.972430 16414.703965 20465.274717

24 2023-01-25 16836.009752 20395.500052 16545.093685 17941.743689

28 2023-01-29 15822.154312 24135.820387 17217.100932 16729.277366

Volume Market Cap


4 784086.534267 3.939071e+08
5 853193.312594 5.990765e+08
6 893487.537225 3.180282e+08
9 898296.347664 4.682099e+08
10 744595.703467 5.868333e+08
12 908228.938806 4.451487e+08
14 881409.058988 5.325931e+08
15 906515.018451 3.470896e+08
16 970019.423516 3.772216e+08
20 814180.628449 4.914450e+08
24 879470.193118 4.909728e+08
28 880156.349030 5.174343e+08

#For Loop and Conditional Statements


df['Price Change'] = df['Close'] - df['Open']

df['Price Trend'] = df.apply(lambda row: 'Up' if row['Close'] >


row['Open'] else 'Down', axis=1)
print(df[['Date', 'Open', 'Close', 'Price Change', 'Price Trend']])

Date Open Close Price Change Price Trend


0 2023-01-01 16144.243872 18684.604178 2540.360306 Up
1 2023-01-02 18755.360360 16365.262378 -2390.097982 Down
2 2023-01-03 15607.716807 24002.368427 8394.651620 Up
3 2023-01-04 17434.177937 20665.980478 3231.802541 Up
4 2023-01-05 17005.642760 21404.929413 4399.286653 Up
5 2023-01-06 16798.332183 19672.714263 2874.382079 Up
6 2023-01-07 18191.610288 23336.592394 5144.982106 Up
7 2023-01-08 19368.954282 22638.191585 3269.237303 Up
8 2023-01-09 15471.880923 16591.329862 1119.448939 Up
9 2023-01-10 15622.710262 21872.542150 6249.831887 Up
10 2023-01-11 19462.332526 24453.685320 4991.352794 Up
11 2023-01-12 17843.240157 15366.433870 -2476.806287 Down
12 2023-01-13 16250.347302 22531.650917 6281.303615 Up
13 2023-01-14 18931.845666 20830.877923 1899.032257 Up
14 2023-01-15 19796.237447 21313.114311 1516.876864 Up
15 2023-01-16 17652.524327 24610.047470 6957.523143 Up
16 2023-01-17 15036.057382 24881.993283 9845.935901 Up
17 2023-01-18 17132.153136 20353.414153 3221.261017 Up
18 2023-01-19 17436.845492 21167.769653 3730.924162 Up
19 2023-01-20 17764.927091 17484.708241 -280.218849 Down
20 2023-01-21 17594.590039 20465.274717 2870.684678 Up
21 2023-01-22 17313.883867 15125.677998 -2188.205869 Down
22 2023-01-23 16148.102805 16106.673900 -41.428905 Down
23 2023-01-24 15190.447443 20285.045461 5094.598018 Up
24 2023-01-25 16836.009752 17941.743689 1105.733938 Up
25 2023-01-26 16330.529328 15236.534667 -1093.994662 Down
26 2023-01-27 16192.060919 24958.580987 8766.520068 Up
27 2023-01-28 15496.457816 17817.318629 2320.860813 Up
28 2023-01-29 15822.154312 16729.277366 907.123054 Up
29 2023-01-30 16982.305783 23644.095779 6661.789996 Up

#close the project by analysing the bitcoin data

You might also like