CS401-movies-analysis/data_loading.py at main · TashkovskaMatea/CS401-movies-analysis · GitHub

1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
#
import pandas as pd

# Necessary paths to load the datasets
DATA_PATH = "./data/"
DATA_PATH_MOVIESUMMARIES = DATA_PATH + "MovieSummaries/"
DATA_PATH_TMDB = DATA_PATH + "TMDB/"
DATA_PATH_IMDB = DATA_PATH + "IMDBData/"
DATA_PATH_FINANCIAL = DATA_PATH + "Financial/"

DATASET_PATH = {
    "movie_metadata": DATA_PATH_MOVIESUMMARIES + "movie.metadata.tsv",
    "plot_summaries": DATA_PATH_MOVIESUMMARIES + "plot_summaries.txt",
    "movie_budget": DATA_PATH_TMDB + "movies_metadata.csv",
    "imdb_ratings": DATA_PATH_IMDB + "title.ratings.tsv",
    "imdb_basics": DATA_PATH_IMDB + "title.basics.tsv",
    "cpi_data": DATA_PATH_FINANCIAL + "CPI.csv",
    "gdp_data": DATA_PATH_FINANCIAL + "GDP.csv",
}

# Column names for each dataset
DATASET_COLUMNS = {
    "movie_metadata": [
        "wikipedia_id",
        "freebase_movie_id",
        "title",
        "release_date",
        "revenue",
        "runtime",
        "languages",
        "countries",
        "genres",
    ],
    "plot_summaries": [
        "wikipedia_id",
        "plot",
    ],
    "movie_budget": [
        "budget",
        "imdb_id",
        "original_title",
        "popularity",
        "release_date",
        "revenue",
        "runtime",
        "title",
        "vote_average",
        "vote_count",
    ],
    "imdb_ratings": ["imdb_id", "imdb_rating", "num_votes"],
    "imdb_basics": [
        "imdb_id",
        "title_type",
        "primary_title",
        "title",
        "is_adult",
        "year",
        "end_year",
        "runtime",
        "genres",
    ],
}

# Data types for the datasets
DATASET_TYPES = {
    "movie_metadata": {
        "wikipedia_id": "string",
        "freebase_movie_id": "string",
        "title": "string",
        "release_date": "string",
        "revenue": "float64",
        "runtime": "float64",
        "languages": "object",
        "countries": "object",
        "genres": "object",
    },
    "plot_summaries":{
        "wikipedia_id": "string",
        "plot": "string",
    },
    "movie_budget": {
        "budget": "object",
        "imdb_id": "string",
        "original_title": "object",
        "popularity": "object",
        "release_date": "object",
        "revenue": "float64",
        "runtime": "float64",
        "title": "object",
        "vote_average": "float64",
        "vote_count": "float64",
    },
    "imdb_ratings": {
        "imdb_id": "string",
        "imdb_rating": "float64",
        "num_votes": "int64",
    },
    "imdb_basics": {
        "imdb_id": "string",
        "title_type": "string",
        "primary_title": "string",
        "title": "string",
        "is_adult": "string",
        "year": "string",
        "end_year": "string",
        "runtime": "string",
        "genres": "string",
    },
}


def load_dataset(name):
    """Loads a dataset from the given name

    Args:
        name (string): Name of the dataset to load

    Returns:
        pandas.DataFrame: The loaded dataset
    """
    sep = "\t"
    header = 0
    skiprows = None

    if name == "movie_metadata" or name == "plot_summaries":
        header = None
    elif name == "movie_budget" or name == "cpi_data" or name == "gdp_data":
        sep = ","
        if name != "movie_budget":
            skiprows = 4

    print("Loading dataset: " + name)

    if name in ["movie_metadata", "imdb_ratings", "imdb_basics", "plot_summaries"]:
        return pd.read_csv(
            DATASET_PATH[name],
            sep=sep,
            header=header,
            names=DATASET_COLUMNS[name],
            dtype=DATASET_TYPES[name],
            skiprows=skiprows,
            index_col=False,
        )
    elif name in ["movie_budget", "cpi_data", "gdp_data"]:
        return pd.read_csv(
            DATASET_PATH[name],
            sep=sep,
            header=header,
            dtype=DATASET_TYPES[name] if name == "movie_budget" else None,
            skiprows=skiprows,
            index_col=False,
            usecols=DATASET_COLUMNS[name] if name == "movie_budget" else None,
        )
    else:
        raise ValueError("Dataset name not found")