4주차 TIL - 데이터가 너무 많아!

import pandas as pd

import matplotlib.pyplot as plt

import seaborn as sns

file_path = "FAO.csv"  # 파일 경로 지정

data = pd.read_csv(file_path, encoding='ISO-8859-1')

columns_to_drop = ['Area Abbreviation', 'Area Code', 'latitude', 'longitude', 'Item Code', 'Element Code']

data_cleaned = data.drop(columns=columns_to_drop)

# 데이터 확인

print(data_cleaned.head())

print(data_cleaned.info())

Area Item Element Unit Y1961 Y1962 \ 0 Afghanistan Wheat and products Food 1000 tonnes 1928.0 1904.0 1 Afghanistan Rice (Milled Equivalent) Food 1000 tonnes 183.0 183.0 2 Afghanistan Barley and products Feed 1000 tonnes 76.0 76.0 3 Afghanistan Barley and products Food 1000 tonnes 237.0 237.0 4 Afghanistan Maize and products Feed 1000 tonnes 210.0 210.0 Y1963 Y1964 Y1965 Y1966 ... Y2004 Y2005 Y2006 Y2007 \ 0 1666.0 1950.0 2001.0 1808.0 ... 3249.0 3486.0 3704.0 4164.0 1 182.0 220.0 220.0 195.0 ... 419.0 445.0 546.0 455.0 2 76.0 76.0 76.0 75.0 ... 58.0 236.0 262.0 263.0 3 237.0 238.0 238.0 237.0 ... 185.0 43.0 44.0 48.0 4 214.0 216.0 216.0 216.0 ... 120.0 208.0 233.0 249.0 Y2008 Y2009 Y2010 Y2011 Y2012 Y2013 0 4252.0 4538.0 4605.0 4711.0 4810 4895 1 490.0 415.0 442.0 476.0 425 422 2 230.0 379.0 315.0 203.0 367 360 3 62.0 55.0 60.0 72.0 78 89 4 247.0 195.0 178.0 191.0 200 200 [5 rows x 57 columns] <class 'pandas.core.frame.DataFrame'> RangeIndex: 21477 entries, 0 to 21476 Data columns (total 57 columns): # Column Non-Null Count Dtype --- ------ -------------- ----- 0 Area 21477 non-null object 1 Item 21477 non-null object 2 Element 21477 non-null object 3 Unit 21477 non-null object 4 Y1961 17938 non-null float64 5 Y1962 17938 non-null float64 6 Y1963 17938 non-null float64 7 Y1964 17938 non-null float64 8 Y1965 17938 non-null float64 9 Y1966 17938 non-null float64 10 Y1967 17938 non-null float64 11 Y1968 17938 non-null float64 12 Y1969 17938 non-null float64 13 Y1970 17938 non-null float64 14 Y1971 17938 non-null float64 15 Y1972 17938 non-null float64 16 Y1973 17938 non-null float64 17 Y1974 17938 non-null float64 18 Y1975 17938 non-null float64 19 Y1976 17938 non-null float64 20 Y1977 17938 non-null float64 21 Y1978 17938 non-null float64 22 Y1979 17938 non-null float64 23 Y1980 17938 non-null float64 24 Y1981 17938 non-null float64 25 Y1982 17938 non-null float64 26 Y1983 17938 non-null float64 27 Y1984 17938 non-null float64 28 Y1985 17938 non-null float64 29 Y1986 17938 non-null float64 30 Y1987 17938 non-null float64 31 Y1988 17938 non-null float64 32 Y1989 17938 non-null float64 33 Y1990 18062 non-null float64 34 Y1991 18062 non-null float64 35 Y1992 20490 non-null float64 36 Y1993 20865 non-null float64 37 Y1994 20865 non-null float64 38 Y1995 20865 non-null float64 39 Y1996 20865 non-null float64 40 Y1997 20865 non-null float64 41 Y1998 20865 non-null float64 42 Y1999 20865 non-null float64 43 Y2000 21128 non-null float64 44 Y2001 21128 non-null float64 45 Y2002 21128 non-null float64 46 Y2003 21128 non-null float64 47 Y2004 21128 non-null float64 48 Y2005 21128 non-null float64 49 Y2006 21373 non-null float64 50 Y2007 21373 non-null float64 51 Y2008 21373 non-null float64 52 Y2009 21373 non-null float64 53 Y2010 21373 non-null float64 54 Y2011 21373 non-null float64 55 Y2012 21477 non-null int64 56 Y2013 21477 non-null int64 dtypes: float64(51), int64(2), object(4) memory usage: 9.3+ MB None