Data Cleaning, Exploration of Unstructured Dataset

# coding: utf-8

# In[1]:

# Importing Libraries
import pandas as pd


# In[2]:

# Create an object and Load the dataset
NY_FireDept_ds = pd.read_csv('C:\\Users\\pravinw\\Documents\\DATA SCIENTIST\\FDNY\\FDNY.csv')


# In[3]:

# View the content
NY_FireDept_ds.describe


# In[4]:

# View the first 5 records
NY_FireDept_ds.head()


# In[5]:

# Skip the Duplicate Header row
NY_FireDept_ds = pd.read_csv('C:\\Users\\pravinw\\Documents\\Fractal\\DATA SCIENTIST\\FDNY\\FDNY.csv', skiprows=1)


# In[6]:

# Verify the Dataset
NY_FireDept_ds.head()


# In[7]:

# Data Statistics
NY_FireDept_ds.describe()


# In[8]:

# View the attributes
NY_FireDept_ds.columns


# In[9]:

# View the index of the dataset
NY_FireDept_ds.index


# In[10]:

# Count of records of each attribute
NY_FireDept_ds.count()


# In[11]:

# view datatype of all attribute
NY_FireDept_ds.dtypes


# In[12]:

# Group the borough
groupby_borough = NY_FireDept_ds.groupby('Borough')


# In[13]:

# Individual Borough count
groupby_borough.size()


# In[14]:

# Select Fire Dept information for Manhattan
Manhattan_borough = groupby_borough.get_group('Manhattan')


# In[15]:

# View the Manhattan Fire Information
Manhattan_borough