import pandas as pd
import os

print pd.__version__

DATA_DIR = '../data'
# reading table
# making seperator as comma
# renaming column names for 0th row of the file
df = pd.read_table(
                   os.path.abspath(os.path.join(DATA_DIR,'day1/iris.csv')), 
                   sep=',',
                   header=0,
                   names=['sepal_len', 'sepal_wid', 'petal_len', 'petal_wid', 'class']
                  )
df.head(5)

# see dimension of the dataset
# 150 rows, 5 columns
df.shape

# drop method takes the column names in array
# axis=1 corresponds to columns
# inplace=True does not require you to hold it in other variable, memory efficient
df.drop(['class'], axis=1, inplace=True)
df.head(5)

# drop method takes the row names in array
# axis=0 corresponds to rows, bydefault axis=0 in drop method
# inplace=True does not require you to hold it in other variable, memory efficient
df.drop([0, 1], axis=0, inplace=True)
df.head(5)

df = pd.read_table(
                   'http://bit.ly/imdbratings', 
                   sep=','
                  )
df.head(5)

# sort_values() method returns bydefault by ascending order
# sort_values() can take 'inplace=True/False' for changing the values inplace
print df['star_rating'].sort_values().head(5)
print df['star_rating'].sort_values().tail(5)

# ascending=True/False parameter in sort_values() can decide the sorting order
print df['star_rating'].sort_values(ascending=False).head(5)
print df['star_rating'].sort_values(ascending=False).tail(5)

# relatively better way to do is to use the below mentioned technique
# to sort by multiple fields, just populate the array inside sort_values()
df.sort_values(['duration'], ascending=True).head(5)

df = pd.read_table(
                   'http://bit.ly/imdbratings', 
                   sep=','
                  )
df.head(5)

# we need movies above 8.5
df_rating_bools = df['star_rating'].map(lambda row: row>8.5)
df[df_rating_bools].tail(5)

# we need movies above 8.5
boolean = list()
for row in df['star_rating']:
    if row > 8.5: boolean.append(True)
    else: boolean.append(False)

# boolean is a list, and since column in pandas is a series, so we need to convert list to series
df_rating_bools = pd.Series(boolean)
df[df_rating_bools].tail(5)

# df['star_rating'] > 8.5 automatically searches/iterates through all the rows satisying this condition
df[df['star_rating'] > 8.5].tail(5)

df = pd.read_table(
                   'http://bit.ly/imdbratings', 
                   sep=','
                  )
df.head(5)

# we want movies that have rating above  8.5 and duration above 200mins
df[(df['star_rating'] > 8.5) & (df['duration'] > 200)].head(5)

df_rating_bools = df['star_rating'].map(lambda row: row>8.5)
df_duration_bools = df['duration'].map(lambda row: row>200)
df[df_rating_bools & df_duration_bools].tail(5)

# this appoarch is inspired by python 'if in [1,2]' functionality
bools = df['genre'].isin(['Drama', 'Action'])
df[bools].head(5)