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

# # Pandas_QuickStart
# Origin from http://pandas.pydata.org/pandas-docs/stable/  
# by [openthings@163.com](http://my.oschina.net/u/2306127/blog?catalog=3420733), 2016-04.  
# 
# ## 6.1 Object Creation
# Creating a Series by passing a list of values, letting pandas create a default integer index:  

# In[1]:


import pandas as pd
import numpy as np
import matplotlib.pyplot as plt

s = pd.Series([1,3,5,np.nan,6,8])
s


# Creating a DataFrame by passing a numpy array, with a datetime index and labeled columns:

# In[2]:


dates = pd.date_range('20130101', periods=6)
dates


# In[7]:


df = pd.DataFrame(np.random.randn(6,4), index=dates, columns=list('ABCD'))

df


# Creating a DataFrame by passing a dict of objects that can be converted to series-like.

# In[8]:


df2 = pd.DataFrame({ 'A' : 1.,
'B' : pd.Timestamp('20130102'),
'C' : pd.Series(1,index=list(range(4)),dtype='float32'),
'D' : np.array([3] * 4,dtype='int32'),
'E' : pd.Categorical(["test","train","test","train"]),
'F' : 'foo' })

df2


# In[9]:


df2.dtypes


# If you’re using IPython, tab completion for column names (as well as public attributes) is automatically enabled. Here’s a subset of the attributes that will be completed:
#     
#     In [13]: df2.<TAB>

# In[11]:


df2.


# As you can see, the columns A, B, C, and D are automatically tab completed. E is there as well; the rest of the attributes have been truncated for brevity.

# ## 6.2 Viewing Data

# In[14]:


df.head()


# In[15]:


df.tail(3)


# In[16]:


df.index


# In[17]:


df.values


# In[18]:


df.describe()


# In[19]:


df.T


# In[20]:


df.sort_index(axis=1, ascending=False)


# In[21]:


df.sort_values(by='B')


# ## 6.3 Selection

# Getting

# In[22]:


df['A']


# In[23]:


df[0:3]


# In[24]:


df['20130102':'20130104']


# ### 6.3.2 Selection by Label

# For getting a cross section using a label

# In[25]:


df.loc[dates[0]]


# Selecting on a multi-axis by label

# In[26]:


df.loc[:,['A','B']]


# Showing label slicing, both endpoints are included

# In[27]:


df.loc['20130102':'20130104',['A','B']]


# Reduction in the dimensions of the returned object

# In[30]:


df.loc['20130102',['A','B']]


# For getting a scalar value

# In[31]:


df.loc[dates[0],'A']


# For getting fast access to a scalar (equiv to the prior method)

# In[32]:


df.at[dates[0],'A']


# ### 6.3.3 Selection by Position
# See more in Selection by Position
# Select via the position of the passed integers

# In[33]:


df.iloc[3]


# By integer slices, acting similar to numpy/python

# In[34]:


df.iloc[3:5,0:2]


# By lists of integer position locations, similar to the numpy/python style

# In[35]:


df.iloc[[1,2,4],[0,2]]


# For slicing rows explicitly

# In[36]:


df.iloc[1:3,:]


# For slicing columns explicitly

# In[37]:


df.iloc[:,1:3]


# For getting a value explicitly

# In[39]:


df.iloc[1,1]


# For getting fast access to a scalar (equiv to the prior method)

# In[40]:


df.iat[1,1]


# ### 6.3.4 Boolean Indexing

# Using a single column’s values to select data.

# In[41]:


df[df.A > 0]


# A where operation for getting.

# In[42]:


df[df > 0]


# #### Using the isin() method for filtering:

# In[43]:


df2 = df.copy()


# 添加一列。

# In[44]:


df2['E'] = ['one', 'one','two','three','four','three']


# In[45]:


df2


# In[46]:


df2[df2['E'].isin(['two','four'])]


# ### 6.3.5 Setting
# Setting a new column automatically aligns the data by the indexes

# In[48]:


s1 = pd.Series([1,2,3,4,5,6], index=pd.date_range('20130102', periods=6))
s1


# Setting values by position

# In[49]:


df.iat[0,1] = 0


# Setting by assigning with a numpy array

# In[50]:


df.loc[:,'D'] = np.array([5] * len(df))


# The result of the prior setting operations

# In[51]:


df


# A where operation with setting.

# In[52]:


df2 = df.copy()


# In[53]:


df2[df2 > 0] = -df2


# In[54]:


df2


# In[ ]: