#!/usr/bin/env python
# coding: utf-8

# In[37]:


import re
import numpy as np
import pandas as pd


# In[50]:


numlist=["$10000","$20,000","30,000",40000,"50000   "]


# In[51]:


for i,value in enumerate(numlist):
    numlist[i]=re.sub(r"([$,])","",str(value))
   


# In[52]:


numlist


# In[54]:


int(numlist[1])


# In[56]:


for i,value in enumerate(numlist):
    numlist[i]=int(value)


# In[57]:


numlist


# In[58]:


np.mean(numlist)


# In[59]:


numlist2=str(numlist)


# In[60]:


numlist2.split(None,0)


# In[61]:


numlist2.split(None,0)[0]


# In[62]:


titanic =pd.read_csv("https://vincentarelbundock.github.io/Rdatasets/csv/datasets/Titanic.csv")


# In[65]:


titanic=titanic.drop('Unnamed: 0', 1)


# In[66]:


titanic.info()


# In[67]:


titanic.head()


# In[69]:


a=titanic.iloc[:,1:]
b=titanic.iloc[:,1:].values

print(type(titanic))
print(type(a))
print(type(b))


# In[70]:


a


# In[71]:


b


# In[75]:


titanic.columns[1:]


# In[76]:


titanic.as_matrix(columns=titanic.columns[1:])


# In[81]:


data=titanic.as_matrix(columns=titanic.columns[1:])


# In[86]:


len(data)


# In[91]:


range(0,len(data))


# In[92]:


g=pd.DataFrame(data=data[0:,0:],    # values
             index=range(0,len(data)),    # 1st column as index
             columns=titanic.columns[1:])  # 1st row as the column names


# In[93]:


g.head()


# In[ ]: