!pip install statsmodels import statsmodels.api as sm import numpy as np # linear algebra import pandas as pd # data processing import seaborn as sns import matplotlib.pyplot as plt import numpy.ma as ma # deal with NaN import scipy.stats from scipy import stats import datetime as dt import plotly.express as px

# Import dataset df = pd.read_csv("tord_v3.csv", delimiter=';', skiprows=0, low_memory=False) #This line solves the ParseError prompt #filter out the relevant columns for analysis later coin_ico = df[['name','country','is_ico','is_ieo','is_sto','ico_start','ico_end','raised_usd','whitelist','kyc','bonus','rating','teamsize','platform','distributed_in_ico']] df.head()

df.describe()

#converting the dates to datetime to minimise inconsistency coin_ico['ico_start'] = pd.to_datetime(coin_ico['ico_start']) coin_ico['ico_end'] = pd.to_datetime(coin_ico['ico_end']) coin_ico['ico_duration'] = coin_ico['ico_end'] - coin_ico['ico_start'] #NEW, only keep coins which have successful ICOs coin_ico = coin_ico[coin_ico['is_ico']== 1] #changing the number of days from datetime format to integer coin_ico["ico_duration"] = coin_ico["ico_duration"].dt.days #getting rid of the NaT values in the ICO date variable coin_ico['ico_start'] = coin_ico['ico_start'].apply(lambda x: x.strftime('%Y-%m-%d')if not pd.isnull(x) else '') coin_ico['ico_end'] = coin_ico['ico_end'].apply(lambda x: x.strftime('%Y-%m-%d')if not pd.isnull(x) else '') #NEW, REPLACED NaN VALUES WITH MEDIAN NUMBERS coin_ico['ico_duration'].fillna(31,inplace=True) coin_ico['raised_usd'].fillna(0,inplace=True) coin_ico['distributed_in_ico'].fillna(0.5,inplace=True) #Winsorize variables def clip_series(s, lower, upper): clipped = s.clip(lower=s.quantile(lower), upper=s.quantile(upper)) return clipped # Manage list of features to be winsorized winsorize_list = ['ico_duration','raised_usd','distributed_in_ico'] for var in winsorize_list: coin_ico[var+'_winsorised'] = clip_series(coin_ico[var], 0.005, 0.995)

#find out the median or mean value of each columns, which informs the pervious step's fillna formula print(coin_ico['ico_duration'].median()) print(coin_ico['raised_usd'].median()) print(coin_ico['distributed_in_ico'].median())

#Creating a dummy variable indicating how successful the Initial Coin Offering is successful a=[] coin_ico['is_successful'] = coin_ico['raised_usd_winsorised'] for row in coin_ico['is_successful']: if row >= 500000: #this line sets the threshold of 500k USD, the prescribed yardstick of a successful ICO. a.append(1) else: a.append(0) coin_ico['is_successful'] = a print(coin_ico['is_successful']) #the 'is_successful' column will now indicate whether the respective tokens had successful ICOs.

#dropping the pre-winsorised columns to rule out collinearity in subsequent data analysis coin_ico = coin_ico.drop(columns=['ico_duration','raised_usd','distributed_in_ico']) coin_ico.head()

print(sum(coin_ico['raised_usd_winsorised']>=500000)/len(coin_ico)) # calculate the successful fund raising rate if the soft cap is set to $500000 as stated in the reference paper.

#Creating a dummy variable represented by 2 columns with regards to whether the respective stock is on whitelist coin_ico = pd.get_dummies(coin_ico, columns=['whitelist']) coin_ico.head()

#General visualisation of correlations amongst the variables created & cleaned f, ax = plt.subplots(figsize=(10, 8)) corr = coin_ico.corr() # Generate a custom diverging colormap cmap = sns.diverging_palette(230, 20, as_cmap=True) # Plot heatmap sns.heatmap(corr, cmap=cmap, square=True, ax=ax)

#g = sns.pairplot(coin_ico[['is_successful','ico_duration', 'is_ico', 'raised_usd', 'kyc','rating','bonus','teamsize','whitelist_No','whitelist_Yes','country']], hue='is_successful',palette='gnuplot2') #g.fig.suptitle("Pairplot, colour-coded with country of origin",y=1.1)

def successful_visual(dependent, independent, dataframe,colour): fig = px.scatter( dataframe[dataframe[independent] != None], x=independent, y=dependent, color=colour, title="Successfulness:" + dependent, marginal_y="violin", marginal_x="box", ) fig.show()

successful_visual('raised_usd_winsorised', 'rating', coin_ico,'rating')

successful_visual('raised_usd_winsorised', 'ico_duration_winsorised', coin_ico,'distributed_in_ico_winsorised')

successful_visual('country', 'raised_usd_winsorised', coin_ico,'raised_usd_winsorised')

#regression trials X = coin_ico[['teamsize','rating','ico_duration_winsorised','distributed_in_ico_winsorised']] y = coin_ico['raised_usd_winsorised'] # Note the difference in argument order X = sm.add_constant(X) model = sm.OLS(y.astype(float), X.astype(float), missing='drop').fit() predictions = model.predict(X.astype(float)) # make the predictions by the model # Print out the statistics print(model.summary())

#regression trials X = coin_ico[['teamsize','rating','ico_duration_winsorised','distributed_in_ico_winsorised']] y = coin_ico['raised_usd_winsorised'] # Note the difference in argument order X = sm.add_constant(X) model = sm.OLS(y.astype(float), X.astype(float), missing='drop').fit() predictions = model.predict(X.astype(float)) # make the predictions by the model # Print out the statistics print(model.summary())

#regression trials logit model coin_ico['log_rating'] = np.log(coin_ico['rating']) X = coin_ico[['teamsize','log_rating','kyc','whitelist_No','ico_duration_winsorised']] y = coin_ico['is_successful'] # Note the difference in argument order X = sm.add_constant(X) model = sm.Logit(y, X.astype(float), missing='drop').fit() # Print out the statistics print(model.summary2())

average_marginal_effect = model.get_margeff(at = "mean", method = "dydx") print(average_marginal_effect.summary())

sns.regplot(x = 'teamsize', y = "is_successful", data = coin_ico,logistic=True) plt.ylabel("Probability of Successful ICO") plt.xlabel("Team Size")

sns.regplot(x = 'log_rating', y = "is_successful", data = coin_ico,logistic=True) plt.ylabel("Probability of Successful ICO") plt.xlabel("Logarithmic form of Rating")

sns.regplot(x = 'kyc', y = "is_successful", data = coin_ico,logistic=True) plt.ylabel("Probability of Successful ICO") plt.xlabel("Know Your Customer Dummy Variable")

sns.regplot(x = 'whitelist_No', y = "is_successful", data = coin_ico,logistic=True) plt.ylabel("Probability of Successful ICO") plt.xlabel("Not being on White List Dummy Variable ")

sns.regplot(x = 'ico_duration_winsorised', y = "is_successful", data = coin_ico,logistic=True) plt.ylabel("Probability of Successful ICO") plt.xlabel("ICO Duration")