import pandas as pd

df = pd.read_csv("IMDB-Movie-Data.csv")
df.head()

df['AvgRating'] = (df['Rating'] + df['Metascore']/10)/2

def custom_rating(genre,rating):
    if 'Thriller' in genre:
        return min(10,rating+1)
    elif 'Comedy' in genre:
        return max(0,rating-1)
    elif 'Drama' in genre:
        return max(5, rating-1)
    else:
        return rating

df["CustomRating"] = df.apply(lambda x: custom_rating(x['Genre'], x['Rating']), axis = 1)

# 單個條件，評分大于5分的
df_gt_5 = df[df['Rating']>5]

# 多個條件: AND - 同時滿足評分高于5分并且投票大于100000的
And_df = df[(df['Rating']>5) & (df['Votes']>100000)]

# 多個條件: OR - 滿足評分高于5分或者投票大于100000的
Or_df = df[(df['Rating']>5) | (df['Votes']>100000)]

# 多個條件：NOT - 將滿足評分高于5分或者投票大于100000的數(shù)據(jù)排除掉
Not_df = df[~((df['Rating']>5) | (df['Votes']>100000))]

df[len(df['Title'].split(" "))>=5]

AttributeError: 'Series' object has no attribute 'split'

#創(chuàng)建一個新的列來存儲每一影片名的長度
df['num_words_title'] = df.apply(lambda x : len(x['Title'].split(" ")),axis=1)

#篩選出影片名長度大于5的部分
new_df = df[df['num_words_title']>=5]

new_df = df[df.apply(lambda x : len(x['Title'].split(" "))>=5,axis=1)]

year_revenue_dict = df.groupby(['Year']).agg({'Revenue(Millions)':np.mean}).to_dict()['Revenue(Millions)']

def bool_provider(revenue, year):
    return revenue<year_revenue_dict[year]

new_df = df[df.apply(lambda x : bool_provider(x['Revenue(Millions)'],x['Year']),axis=1)]

df.loc[lambda x: (x["Rating"] > 5) & (x["Rating"] < 8)][["Title", "Revenue (Millions)"]]

df['Price'].astype('int')

ValueError: invalid literal for int() with base 10: '12,000'

df['Price'] = df.apply(lambda x: int(x['Price'].replace(',', '')),axis=1)

from tqdm import tqdm, tqdm_notebook
tqdm_notebook().pandas()

df["CustomRating"] = df.progress_apply(lambda x: custom_rating(x['Genre'],x['Rating']),axis=1)

Bigger = lambda x, y : x if(x > y) else y
Bigger(2, 10)

df['Rating'].apply(lambda x:"低分電影" if x < 3 else ("中等電影" if x>=3 and x < 5 else("高分電影" if x>=8 else "值得觀看")))