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

# # Pandas Basics

# In[26]:


import pandas as pd

print(pd.__version__)


# ## Panda Series

# ### A Pandas Series is like a column in a table.
# 
# *It is a one-dimensional array holding data of any type.*

# In[13]:


a = [1, 7, 2]

myvar = pd.Series(a)

print(myvar)


# In[17]:


print(myvar[1])


# - **With the index argument, you can name your own labels.**

# In[14]:


a = [1, 7, 2]

myvar = pd.Series(a, index = ["x", "y", "z"])

print(myvar)


# In[19]:


print(myvar["y"])


# - **You can also use a key/value object, like a dictionary, when creating a Series.**

# In[20]:


calories = {"day1": 420, "day2": 380, "day3": 390}

myvar = pd.Series(calories)

print(myvar)


# ****The keys of the dictionary become the labels.*

# In[21]:


print(myvar['day1'])


# - **To select only some of the items in the dictionary, use the index argument and specify only the items you want to include in the Series.**

# In[23]:


calories = {"day1": 420, "day2": 380, "day3": 390}

myvar = pd.Series(calories, index = ["day1", "day2"])

print(myvar)


# ## Pandas Data Frame

# ### Data sets in Pandas are usually multi-dimensional tables, called DataFrames.
# 
# *Series is like a column, a DataFrame is the whole table.*

# In[48]:


data = {
  "calories": [420, 380, 390],
  "duration": [50, 40, 45]
}

df = pd.DataFrame(data)

print(df)


# ### Locate Row
# 
# *Pandas use the loc attribute to return one or more specified row(s)*

# In[49]:


print(df.loc[0])


# ****This example returns a Pandas Series.*

# In[50]:


print(df.loc[[0, 1]])


# **** When using [ ], the result is a Pandas DataFrame.*

# In[35]:


data = {
  "calories": [420, 380, 390],
  "duration": [50, 40, 45]
}

df = pd.DataFrame(data, index = ["day1", "day2", "day3"])

print(df) 


# In[36]:


print(df.loc["day2"])


# ### Load Files Into a DataFrame

# In[51]:


df = pd.read_csv('pokemon_data.csv')

print(df)