CryptoCurrency Analysis

Cryptocurrency:

A cryptocurrency (or crypto currency or crypto for short) is a digital asset designed to work as a medium of exchange wherein individual coin ownership records are stored in a ledger existing in a form of computerized database using strong cryptography to secure transaction records, to control the creation of additional coins, and to verify the transfer of coin ownership.

The cryptocurrency market has been volatile from the very beginning, but the last couple of years have been a particularly wild ride for millions of investors around the world. Many have made millions on the big upswings, and yet many have lost large and small investments in the bursting bubbles and sudden market downturns.

Understanding the Problem:

In the given assignment we have been given consolidated financial information for the top 10 cryptocurrencies by market cap extracted from CoinMarketCap.com. We want to understand how the prices of these currencies have changed over the course of time and also we want to see the top 3 currencies change in volume over the period of 2016-2019. This will be done for people of two age groups of 17-35 and 60+.

Gathering Data:

Once the requirements are clearly understood, the data will then be loaded into python jupyter notebook using pandas library. Once data has been uploaded and viewable, we will check its data type to understand what kind of data we are dealing with. From the given set of data, we will extract the following columns:

1) Currency (Object) 2) Date (Datetime) 3) High (Float) 4) Volume (Int)

Data Wrangling , Validation and Creating Pivot Tables:

We will convert the data types to continuous variables so that we can create visualizations. We will also then check for missing data and deal with them accordingly. Once the data has been cleansed, we will now move towards visualization. In order to create the required visuals we will first create two more dataframes in order to meet the required visuals. We will create a dataframe consisting of Currency,Date and High for the first visual, and for the Second Data frame we will select Currency,Date and Volume for the second visual. These dataframes will be converted into pivot tables setting Date as index, Currency as column and High as value in first dataframe where as in the second dataframe, we will first filter the Date to show values from 2016-2019 and top 3 Currencies I.e Bitcoin, Ethereum and Tether and then convert the dataframe into a pivot table where Date is index, Currency is Column and Volume are values.

Visualization:

After creating the pivot tables we will create line plot and box plot using matplotlib for the first requirement. A line graph is commonly used to display change over time as a series of data points connected by straight line segments on two axes. It is simple and clearly shows the change in value over the course of time. Box plots are a type of graph that can help visually organize data. Once the box plot is graphed, you can display and compare distributions of data. These visuals are useful particularly in financial analysis and can cater both age groups. The colors used will be sober and visualy appealing to both age groups.

For the second requirement we will again create a line plot and a bar plot using matplotlib. The reason for line graphs is same as it was in the first requirement whereas A bar chart or bar graph is a chart or graph that presents categorical data with rectangular bars with heights or lengths proportional to the values that they represent. It is another simple representation and shows the change in volume over a course of time.

Importing Required Libraries

import pandas as pd
import numpy as np
import matplotlib.pylab as plt
import seaborn as sns
%matplotlib inline 

Reading the CSV File

df = pd.read_csv("D:\\Documents\\Assignment\\consolidated_coin_data.csv", delimiter=",")
print ('Data read into a pandas dataframe!')

Data read into a pandas dataframe!

df.head() #Calling first 5 rows

	Currency	Date	Open	High	Low	Close	Volume	Market Cap
0	tezos	4-Dec-19	1.29	1.32	1.25	1.25	46048752	824588509
1	tezos	3-Dec-19	1.24	1.32	1.21	1.29	41462224	853213342
2	tezos	2-Dec-19	1.25	1.26	1.20	1.24	27574097	817872179
3	tezos	1-Dec-19	1.33	1.34	1.25	1.25	24127567	828296390
4	tezos	30-Nov-19	1.31	1.37	1.31	1.33	28706667	879181680

df.dtypes #Checking Datatypes

Currency       object
Date           object
Open          float64
High          float64
Low           float64
Close         float64
Volume          int64
Market Cap      int64
dtype: object

df['Date'] = pd.to_datetime(df['Date'])
df[['Date']] = pd.DatetimeIndex(df['Date']).year #Converting Datatypes to years for better representation

df.dtypes #Checking updated column

Currency       object
Date            int64
Open          float64
High          float64
Low           float64
Close         float64
Volume          int64
Market Cap      int64
dtype: object

df.describe() #Understanding the data

	Date	Open	High	Low	Close	Volume	Market Cap
count	28944.000000	28944.000000	28944.000000	28944.000000	28944.000000	2.894400e+04	2.894400e+04
mean	2016.111940	300.719748	309.832808	290.858372	300.947362	8.133058e+08	7.194826e+09
std	1.920268	1373.884718	1416.598612	1325.072673	1374.461259	3.059516e+09	2.469322e+10
min	2013.000000	0.000000	0.000000	0.000000	0.000000	0.000000e+00	0.000000e+00
25%	2014.000000	0.210000	0.210000	0.200000	0.210000	2.418700e+05	6.345143e+07
50%	2016.000000	2.995000	3.090000	2.880000	2.980000	5.212684e+06	3.453673e+08
75%	2018.000000	24.430000	25.530000	23.270000	24.430000	1.554764e+08	3.422403e+09
max	2019.000000	19475.800000	20089.000000	18974.100000	19497.400000	5.350913e+10	3.265025e+11

df.info(verbose=False) #Information about the dataframe

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 28944 entries, 0 to 28943
Columns: 8 entries, Currency to Market Cap
dtypes: float64(4), int64(3), object(1)
memory usage: 1.8+ MB

Checking for Missing Data

missing_data = df.isnull()
missing_data.head(5)

	Currency	Date	Open	High	Low	Close	Volume	Market Cap
0	False	False	False	False	False	False	False	False
1	False	False	False	False	False	False	False	False
2	False	False	False	False	False	False	False	False
3	False	False	False	False	False	False	False	False
4	False	False	False	False	False	False	False	False

df.isnull().sum()

Currency      0
Date          0
Open          0
High          0
Low           0
Close         0
Volume        0
Market Cap    0
dtype: int64

df.corr() #Checking Correlation between columns

	Date	Open	High	Low	Close	Volume	Market Cap
Date	1.000000	0.184136	0.183393	0.185257	0.184023	0.345563	0.268524
Open	0.184136	1.000000	0.999268	0.998868	0.998551	0.560011	0.953660
High	0.183393	0.999268	1.000000	0.998588	0.999403	0.561062	0.954377
Low	0.185257	0.998868	0.998588	1.000000	0.999205	0.559677	0.954393
Close	0.184023	0.998551	0.999403	0.999205	1.000000	0.560457	0.955012
Volume	0.345563	0.560011	0.561062	0.559677	0.560457	1.000000	0.591818
Market Cap	0.268524	0.953660	0.954377	0.954393	0.955012	0.591818	1.000000

To view the dimensions of the dataframe, we use the .shape parameter.

df.shape # size of dataframe (rows, columns)  

(28944, 8)

df1 = df[['Currency','Date','High']] #creating new dataframe

df1 = df1.groupby(['Currency','Date'],as_index=False).max() #Using groupby function to create required pivot table
df1 

	Currency	Date	High
0	binance-coin	2013	53.15
1	binance-coin	2014	32.06
2	binance-coin	2015	8.73
3	binance-coin	2016	5.95
4	binance-coin	2017	53.55
...	...	...	...
79	xrp	2015	0.02
80	xrp	2016	0.01
81	xrp	2017	2.85
82	xrp	2018	3.84
83	xrp	2019	0.51

84 rows × 3 columns

grouped_pivot = df1.pivot(index='Date',columns='Currency',values='High') #Creating Pivot Table
grouped_pivot

Currency	binance-coin	bitcoin	bitcoin-cash	bitcoin-sv	cardano	eos	ethereum	litecoin	stellar	tether	tezos	xrp
Date
2013	53.15	1156.14	147.49	53.15	53.15	53.15	1156.14	53.15	53.15	147.49	53.15	147.49
2014	32.06	1017.12	0.03	32.06	32.06	32.06	1017.12	32.06	32.06	0.03	32.06	0.03
2015	8.73	495.56	1.22	8.73	0.01	8.73	320.43	8.73	0.01	1.22	0.01	0.02
2016	5.95	979.40	1.01	5.95	0.00	5.95	21.52	5.95	0.00	1.01	0.00	0.01
2017	53.55	20089.00	4355.62	53.55	0.78	53.55	881.94	375.29	0.39	1.21	12.19	2.85
2018	24.91	17712.40	3071.16	243.79	1.33	22.89	1432.88	323.11	0.94	1.07	7.55	3.84
2019	39.57	13796.49	522.09	255.88	0.11	8.59	361.40	146.43	0.16	1.06	1.83	0.51

plt.style.use(['bmh']) # bmh Styling used for Visulization

grouped_pivot.plot(kind='line',figsize=(10,5))

plt.title('Change in Price of Currencies',fontsize = 20)
plt.ylabel('Price',fontsize = 15)
plt.xlabel('Years',fontsize = 15)
plt.legend(fontsize = 10)
plt.show()

grouped_pivot.plot(kind='box' ,figsize=(14, 5))

plt.title('Change in Price of Currencies Over the Course of Time')
plt.ylabel('Price')
plt.xlabel('Years')
plt.yticks(np.arange(0, 21000, 2500))
plt.show() # need this line to show the updates made to the figure

df2 = df[['Currency','Date','Volume']]
df2 = df2.groupby(['Currency','Date'],as_index=False).max()

df3 = df2[df2['Date'] > 2015]
df3.head()

	Currency	Date	Volume
3	binance-coin	2016	19773600
4	binance-coin	2017	1730780032
5	binance-coin	2018	637020992
6	binance-coin	2019	742382920
10	bitcoin	2016	363320992

df3_pivot = df3.pivot(index='Date',columns='Currency',values = 'Volume')
df3_pivot

Currency	binance-coin	bitcoin	bitcoin-cash	bitcoin-sv	cardano	eos	ethereum	litecoin	stellar	tether	tezos	xrp
Date
2016	19773600	363320992	7399410	19773600	2369690	19773600	199408000	19773600	2369690	7399410	2369690	15967600
2017	1730780032	22197999616	11889600512	1730780032	645155968	1730780032	5179829760	6961679872	537916032	4687949824	280844992	8108389888
2018	637020992	23840899072	5377260032	637020992	1713769984	4870720000	9214950400	3481550080	1513270016	6967777735	15960800	9110439936
2019	742382920	45105733173	4522945333	1701098408	340512939	5394932035	18661465873	6442000276	837742777	53509128965	123832790	9415068271

df4 = df3[(df3['Currency'] == 'bitcoin') | (df3['Currency'] == 'ethereum') | (df3['Currency'] == 'tether')]
df4_pivot = df4.pivot(index='Date',columns='Currency',values = 'Volume')
df4_pivot

Currency	bitcoin	ethereum	tether
Date
2016	363320992	199408000	7399410
2017	22197999616	5179829760	4687949824
2018	23840899072	9214950400	6967777735
2019	45105733173	18661465873	53509128965

df4_pivot.plot(kind='bar',figsize=(10, 5))
plt.title('Change in Volume of Top 3 Currencies from 2016-2019', fontsize = 15)
plt.ylabel('Volume')
plt.xlabel('Years')
plt.legend(fontsize = 10)
plt.show() 

df4_pivot.plot(kind='line',figsize=(10, 5)) #Line Chart for 
plt.title('Change in Volume of Top 3 Currencies from 2016-2019 ', fontsize = 15)
plt.ylabel('Volume')
plt.xlabel('Years')
plt.xticks(np.arange(2016, 2020, 1))
plt.legend(fontsize = 10)
plt.show()