import pandas as pd

Creating data

pd.DataFrame({'Yes': [50, 21], 'No': [131, 2]})
pd.DataFrame({'Bob': ['I liked it.', 'It was awful.'], 
              'Sue': ['Pretty good.', 'Bland.']})
pd.DataFrame({'Bob': ['I liked it.', 'It was awful.'], 
              'Sue': ['Pretty good.', 'Bland.']},
             index=['Product A', 'Product B'])

pd.Series([1, 2, 3, 4, 5])
pd.Series([30, 35, 40], index=['2015 Sales', '2016 Sales', '2017 Sales'], 
          name='Product A')

Reading data files

wine_reviews = pd.read_csv("../input/wine-reviews/winemag-data-130k-v2.csv")

wine_reviews.shape

wine_reviews.head()

wine_reviews = pd.read_csv("../input/wine-reviews/winemag-data-130k-v2.csv", index_col=0)
wine_reviews.head()

Naive accessors

reviews
reviews.country
reviews['country']
reviews['country'][0]

Indexing in pandas

reviews.iloc[0]
reviews.iloc[:, 0]
reviews.iloc[:3, 0]
reviews.iloc[1:3, 0]
reviews.iloc[[0, 1, 2], 0]
reviews.iloc[-5:]

reviews.loc[0, 'country']
reviews.loc[:, ['taster_name', 'taster_twitter_handle', 'points']]

Manipulating the index

reviews.set_index("title")

Conditional selection

reviews.country == 'Italy'
reviews.loc[reviews.country == 'Italy']
reviews.loc[(reviews.country == 'Italy') & (reviews.points >= 90)]
reviews.loc[(reviews.country == 'Italy') | (reviews.points >= 90)]
reviews.loc[reviews.country.isin(['Italy', 'France'])]
reviews.loc[reviews.price.notnull()]

Assigning data

reviews['critic'] = 'everyone'
reviews['index_backwards'] = range(len(reviews), 0, -1)

reviews

Summary functions

reviews.points.describe()
reviews.taster_name.describe()
reviews.points.mean()
reviews.taster_name.unique()
reviews.taster_name.value_counts()

Maps

review_points_mean = reviews.points.mean()
reviews.points.map(lambda p: p - review_points_mean)

def remean_points(row):
    row.points = row.points - review_points_mean
    return row

reviews.apply(remean_points, axis='columns')

reviews.head(1)

review_points_mean = reviews.points.mean()
reviews.points - review_points_mean

reviews.country + " - " + reviews.region_1

Groupwise analysis

reviews.groupby('points').points.count()
reviews.groupby('points').price.min()
reviews.groupby('winery').apply(lambda df: df.title.iloc[0])
reviews.groupby(['country', 'province']).apply(lambda df: df.loc[df.points.idxmax()])
reviews.groupby(['country']).price.agg([len, min, max])

Multi-indexes

countries_reviewed = reviews.groupby(['country', 'province']).description.agg([len])
mi = countries_reviewed.index
type(mi)
countries_reviewed.reset_index()

Sorting

countries_reviewed = countries_reviewed.reset_index()
countries_reviewed.sort_values(by='len')
countries_reviewed.sort_values(by='len', ascending=False)
countries_reviewed.sort_index()
countries_reviewed.sort_values(by=['country', 'len'])

Dtypes

reviews.price.dtype
reviews.dtypes
reviews.points.astype('float64')
reviews.index.dtype

Missing data

reviews[pd.isnull(reviews.country)]
reviews.region_2.fillna("Unknown")
reviews.taster_twitter_handle.replace("@kerinokeefe", "@kerino")

Renaming

reviews.rename(columns={'points': 'score'})
reviews.rename(index={0: 'firstEntry', 1: 'secondEntry'})
reviews.rename_axis("wines", axis='rows').rename_axis("fields", axis='columns')

Combining

canadian_youtube = pd.read_csv("../input/youtube-new/CAvideos.csv")
british_youtube = pd.read_csv("../input/youtube-new/GBvideos.csv")

pd.concat([canadian_youtube, british_youtube])

left = canadian_youtube.set_index(['title', 'trending_date'])
right = british_youtube.set_index(['title', 'trending_date'])

left.join(right, lsuffix='_CAN', rsuffix='_UK')