Kaggle Masterに学ぶ機械学習実践アプローチ 写経 02

# %%
print("hello")

# %% [markdown]
# # 過学習について

# %%
import pandas as pd
import duckdb 

# %%
df = pd.read_csv("winequality-red.csv")

# %%
quality_mapping = {
    3:0,
    4:1,
    5:2,
    6:3,
    7:4,
    8:5
}

# %%
df.loc[:, "quality"] = df.quality.map(quality_mapping)

# %%
df

# %%
df = df.sample(frac=1).reset_index(drop=True)

# %%
df

# %%
df_train = df.head(1000)
df_test = df.tail(500)

# %%
df.columns

# %%
from sklearn import tree
from sklearn import metrics

# %%
clf = tree.DecisionTreeClassifier(max_depth=7)
cols = ['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
       'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
       'pH', 'sulphates', 'alcohol']
clf.fit(df_train[cols], df_train.quality)

# %%
train_predictions = clf.predict(df_train[cols])

# %%
test_predictions = clf.predict(df_test[cols])

# %%
train_accuracy = metrics.accuracy_score(df_train.quality, train_predictions)

# %%
test_accyracy = metrics.accuracy_score(df_test.quality, test_predictions)

# %%
train_accuracy

# %%
test_accyracy

# %%
from sklearn import tree 
from sklearn import metrics
import matplotlib
import matplotlib.pyplot as plt
import seaborn as sns 


# %%
matplotlib.rc("xtick", labelsize=20)

# %%
matplotlib.rc("ytick", labelsize=20)

# %%
%matplotlib inline

# %%
train_accuracies = [0.5]
test_accuracies = [0.5]

# %%
cols = ['fixed acidity', 'volatile acidity', 'citric acid', 'residual sugar',
    'chlorides', 'free sulfur dioxide', 'total sulfur dioxide', 'density',
    'pH', 'sulphates', 'alcohol']
for depth in range(1,25):
    clf = tree.DecisionTreeClassifier(max_depth=depth)
    clf.fit(df_train[cols], df_train.quality)
    train_predictions = clf.predict(df_train[cols])
    test_predictions = clf.predict(df_test[cols])    
    train_accuracy = metrics.accuracy_score(df_train.quality, train_predictions)
    test_accuracy= metrics.accuracy_score(df_test.quality, test_predictions)
    train_accuracies.append(train_accuracy)
    test_accuracies.append(test_accuracy)

# %%
plt.figure(figsize=(10,5))

# %%
sns.set_style("whitegrid")
plt.plot(train_accuracies,label = "train_accuracy")
plt.plot(test_accuracies, label="test_accuracy")
plt.legend(loc="upper left", prop={'size':15})
plt.xticks(range(0,26,5))
plt.xlabel("max_depth", size=20)
plt.ylabel("accuracy", size=20)
plt.show()

# %%
names = ['Alice', 'Bob', 'Charlie']
ages = [1,2,3]
for i, (name,age) in enumerate(zip(names,ages)):
    print(i, name, age)

# %%
df

# %% [markdown]
# # kfold法

# %%
df["kfold"] = -1

# %%
df = df.sample(frac=1).reset_index(drop=True)

# %%
df

# %%
from sklearn import model_selection

# %%
kf = model_selection.KFold(n_splits=5)

# %%
type(df)

# %%
df

# %%
for fold, (trn_, val_) in enumerate(kf.split(X=df)):
    df.loc[val_, 'kfold'] = fold 

# %%
df.to_csv("train_folds.csv", index=False)

# %% [markdown]
# # stratifiedKfold

# %%
df["kfold"] = -1

# %%
df =df.sample(frac=1).reset_index(drop=True)

# %%
df

# %%
y=df.quality.values

# %%
kf = model_selection.StratifiedKFold(n_splits=5)

# %%
type(df)

# %%
df

# %%
type(y)

# %%
y

# %%
for i, (trn_, val_) in enumerate(kf.split(X=df, y=y)):
    df.loc[val_, "kfold"] = i

# %%
df.to_csv("train_StratifiedKFold.csv")

# %% [markdown]
# 

# %% [markdown]
# # 回帰データセットに対するkfold

# %%
import numpy as np
import pandas as pd 
from sklearn import datasets
from sklearn import model_selection 

# %%
def create_folds(data):
    data["kfold"] = -1
    data = data.sample(frac=1).reset_index(drop=True)
    num_bins = int(np.floor(1+np.log2(len(data))))
    data["bins"] = pd.cut(data["target"], num_bins, labels=False)
    kf = model_selection.StratifiedKFold(n_splits=5)
    for f, (trn, val) in enumerate(kf.split(X=data, y=data.bins.values)):
        data.loc[val, 'kfold'] = f 
    #data=data.drop("bins", axis=1)
    return data 

# %%
X, y = datasets.make_regression(
    n_samples = 15000, n_features=100, n_targets=1 
)


# %%
type(X)

# %%
X.shape[0]

# %%
df = pd.DataFrame(X, columns=[f"f_{i}" for i in range(X.shape[1])])

# %%
df

# %%
df["target"] = y

# %%
df

# %%
df = create_folds(df)

# %%
df.to_csv("train_bin_StratifiedKFold.csv")

# %%


# %%