【Python】機械学習用無料データセットまとめ

#Scikit Learn ->http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_boston.html#sklearn.datasets.load_boston
# ボストン市の住宅価格データ（Boston house prices dataset）
import pandas as pd
from sklearn.datasets import load_boston

# データフレームのセット
dataset = load_boston()
X = pd.DataFrame(dataset.data, columns=dataset.feature_names)
y = pd.Series(dataset.target, name='MEDV')

# データ形状の確認
print('----------------------------------------')
print('df_boston shape: (%i,%i)' %X.join(y).shape)
print('-----------------------------------------')
display(X.join(y).head(5))

#Scikit Learn -> http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_iris.html#sklearn.datasets.load_iris
# アヤメの品種データ（Iris plants dataset）
import pandas as pd
from sklearn.datasets import load_iris

# データフレームのセット
dataset = load_iris()
X = pd.DataFrame(dataset.data,columns=dataset.feature_names)
y = pd.Series(dataset.target, name='Variety')

# データ形状の確認
print('----------------------------------------')
print('df_iris shape: (%i,%i)' %X.join(y).shape)
print('-----------------------------------------')
display(X.join(y).head(5))()

#Scikit Learn ->http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_breast_cancer.html#sklearn.datasets.load_breast_cancer
#乳がんデータ（Breast cancer wisconsin dataset）
import pandas as pd
from sklearn.datasets import load_breast_cancer

# データフレームのセット
dataset = load_breast_cancer()
X = pd.DataFrame(dataset.data,columns=dataset.feature_names)
y = pd.Series(dataset.target, name='Target')

# データ形状の確認
print('----------------------------------------')
print('df_cancer shape: (%i,%i)' %X.join(y).shape)
print('-----------------------------------------')
display(X.join(y).head(5))

#Scikit Learn -> http://scikit-learn.org/stable/modules/generated/sklearn.datasets.load_digits.html#sklearn.datasets.load_digits
# 数字の手書き文字データ (Optical recognition of handwritten digits dataset)
import pandas as pd
from sklearn.datasets import load_digits

# データフレームのセット
dataset = load_digits(n_class=10)
X = pd.DataFrame(dataset.data,columns=dataset.feature_names)
y = pd.Series(dataset.target, name='Target')

# データ形状の確認
print('----------------------------------------')
print('df_digit shape: (%i,%i)' %X.join(y).shape)
print('-----------------------------------------')
display(X.join(y).head(5))

#Kaggle-> https://www.kaggle.com/unitednations/international-greenhouse-gas-emissions
#国連提供 温室効果ガスデータセット 1990-2017
import pandas as pd
from sklearn.datasets import load_breast_cancer

#データの読み込み　データの保存先は要変更
directory = ["../Data"]
file = ["greenhouse_gas_inventory_data.csv"]

# データフレームのセット
df_emission = pd.read_csv(os.path.join(directory[0], file[0]))
Column_List = df_emission.columns

# データ形状の確認
print('--------------------------------------------------')
print('df_emission_shape: (%i,%i)' % df_emission.shape)
print('--------------------------------------------------')

df_emission.head()

#Kaggle-> https://www.kaggle.com/c/titanic
#タイタニックデータセット (Titanic - Machine Learning from Disaster)
import pandas as pd
from sklearn.datasets import load_breast_cancer

#データの読み込み　データの保存先は要変更
directory = ["../Data"]
file = ["taitanic.csv"]

# データフレームのセット
df_taitanic = pd.read_csv(os.path.join(directory[0], file[0]))
Column_List = df_taitanic.columns

# データ形状の確認
print('--------------------------------------------------')
print('df_taitanic_shape: (%i,%i)' % df_taitanic.shape)
print('--------------------------------------------------')

df_taitanic.head()

#Kaggle-> https://www.kaggle.com/team-ai/bitcoin-price-prediction?select=bitcoin_price_Training+-+Training.csv
#Bitcoin価格予測用データ (Bitcoin Price Prediction (LightWeight CSV))
import pandas as pd
from sklearn.datasets import load_breast_cancer

#データの読み込み　データの保存先は要変更
directory = ["../Data"]
file = ["bitcoin_price_Training - Training.csv"]

# データフレームのセット
df_fintech = pd.read_csv(os.path.join(directory[0], file[0]))
Column_List = df_fintech.columns

# データ形状の確認
print('--------------------------------------------------')
print('df_fintech_shape: (%i,%i)' % df_fintech.shape)
print('--------------------------------------------------')

df_fintech.head()

#Kaggle-> https://www.kaggle.com/NUFORC/ufo-sightings
#UFO目撃データ (UFO Sightings)
import pandas as pd
from sklearn.datasets import load_breast_cancer

#データの読み込み　データの保存先は要変更
directory = ["../Data"]
file = ["ufo_sightings.csv"]

# データフレームのセット
df_ufo = pd.read_csv(os.path.join(directory[0], file[0]))
Column_List = df_ufo.columns

# データ形状の確認
print('--------------------------------------------------')
print('df_ufo_shape: (%i,%i)' % df_ufo.shape)
print('--------------------------------------------------')

df_ufo.head()