就是統測完後寫的一些code
Dataset: Link
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
from sklearn.ensemble import RandomForestRegressor
from sklearn.preprocessing import OneHotEncoder, LabelEncoder
data = pd.read_csv("/content/ds_salaries.csv")
feature = ["experience_level", "employment_type", "salary_in_usd", "company_size", "salary"]
le = LabelEncoder()
for col in data[feature]:
data[col] = le.fit_transform(data[col])
y = data["salary"]
data = data[feature]
x_train, x_test, y_train, y_test = train_test_split(data, y, test_size=0.2, random_state=1)
model = RandomForestRegressor(n_estimators=200, random_state=1)
model.fit(x_train, y_train)
model.score(x_test, y_test)
Dataset: Link
import pandas as pd
from sklearn.ensemble import RandomForestClassifier
from sklearn.preprocessing import LabelEncoder
train_data = pd.read_csv("train.csv")
test_data = pd.read_csv("test.csv")
le = LabelEncoder()
for i in ["Sex", "Age", "Ticket", "Cabin"]:
train_data[i] = le.fit_transform(train_data[i])
test_data[i] = le.fit_transform(test_data[i])
x_train = train_data[["Sex", "Age", "Ticket", "Cabin"]]
y_train = train_data["Survived"]
x_test = test_data[["Sex", "Age", "Ticket", "Cabin"]]
model = RandomForestClassifier(n_estimators=200, random_state=1)
model.fit(x_train, y_train)
prediction = model.predict(x_test)
submission = pd.DataFrame({"PassengerId":test_data["PassengerId"], "Survived":prediction})
submission.to_csv("./submission.csv", index=False)
Dataset: Link
import pandas as pd
from sklearn.model_selection import train_test_split
from nltk import sent_tokenize, word_tokenize
import nltk
from nltk.corpus import stopwords
nltk.download("punkt")
nltk.download("stopwords")
data_train = pd.read_csv('SMSCollection.csv', encoding = "ISO-8859-1")
data_train
x_train, x_test, y_train, y_test = train_test_split(data_train.sms, data_train.Class, test_size = 0.2, random_state = 1)
x_train
from sklearn.feature_extraction.text import TfidfVectorizer
vectorizer = TfidfVectorizer(max_features=2000)
x_train = vectorizer.fit_transform(x_train)
x_test = vectorizer.fit_transform(x_test)
from sklearn import feature_extraction, linear_model
from sklearn.naive_bayes import MultinomialNB
from sklearn import metrics
clf = MultinomialNB().fit(x_train, y_train)
clf.fit(x_train, y_train)
y_pred = clf.predict(x_test)
print(metrics.accuracy_score(y_pred, y_test))
Dataset: Link
from google.colab import files
import os
if(os.path.exists("kaggle.json") == False):
uploaded = files.upload() # 上傳kaggle.json
os.mkdir("/root/.kaggle/")
with open("/root/.kaggle/kaggle.json", 'wb') as f:
f.write(uploaded['kaggle.json'])
!chmod 600 ~/.kaggle/kaggle.json
!kaggle datasets download -d puneet6060/intel-image-classification --unzip
import tensorflow as tf
import numpy as np
from keras.preprocessing.image import ImageDataGenerator
from keras.layers import Input, Add, Dense, Activation, ZeroPadding2D, BatchNormalization, Flatten, Conv2D, AveragePooling2D, MaxPooling2D
from tensorflow.keras.initializers import random_normal, glorot_uniform
from keras import backend as K
import keras
from keras.models import Model, Sequential
train_data_dir = "/content/seg_train"
test_data_dir = "/content/seg_test"
image_generator = ImageDataGenerator(rescale = 1/255, validation_split = 0.2)
train_data = image_generator.flow_from_directory(batch_size = 32,
directory = train_data_dir,
target_size = (224, 224),
subset = "training",
class_mode = "categorical"
)
val_data = image_generator.flow_from_directory(batch_size = 32,
directory = train_data_dir,
target_size = (224, 224),
subset = "training",
class_mode = "categorical"
)
test_gen = ImageDataGenerator(rescale = 1/255)
test_data = test_gen.flow_from_directory(test_data_dir, target_size = (224, 224), batch_size = 32, shuffle = False)
print(train_data.classes)
print(val_data.classes)
print(train_data.class_indices)
print(test_data.classes)
class_names = np.unique(train_data.classes)
def identity_block(x, f, filters):
F1, F2, F3 = filters
x_shortcut = x
x = Conv2D(filters = F1, kernel_size = (1,1), strides = (1,1), padding = "valid",
kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x = Activation("relu")(x)
x = Conv2D(filters = F2, kernel_size = (1,1), strides = (1,1), padding ="same",
kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x = Activation("relu")(x)
x = Conv2D(filters = F3, kernel_size = (1,1), strides = (1,1), padding = "valid",
kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x = Add()([x, x_shortcut])
x = Activation("relu")(x)
return x
def convolutional_block(x, f, filters, s):
F1, F2, F3 = filters
x_shortcut = x
x = Conv2D(F1, (1,1), strides = (s,s), kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x = Activation("relu")(x)
x = Conv2D(F2, (f,f), strides = (1,1), padding = "same", kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x = Activation("relu")(x)
x = Conv2D(F3, (1,1), strides = (1,1), padding = "valid", kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x_shortcut = Conv2D(F3, (1,1), strides = (s,s), padding = "valid", kernel_initializer = glorot_uniform(seed = 1))(x_shortcut)
x_shortcut = BatchNormalization(axis = 3)(x_shortcut)
x = Add()([x, x_shortcut])
x = Activation('relu')(x)
return x
def ResNet50(input_shape = (224, 224, 3), classes = 6):
x_input = Input(input_shape)
x = ZeroPadding2D((3,3))(x_input)
x = Conv2D(64, (7,7), strides = (2,2), kernel_initializer = glorot_uniform(seed = 1))(x)
x = BatchNormalization(axis = 3)(x)
x = Activation("relu")(x)
x = MaxPooling2D((3,3), strides = (2,2))(x)
x = convolutional_block(x, f=3, filters = [64, 64, 256], s = 1)
x = identity_block(x, 3, [64, 64, 256])
x = identity_block(x, 3, [64, 64, 256])
x = convolutional_block(x, f=3, filters = [128, 128, 512], s = 2)
x = identity_block(x, 3, [128, 128, 512])
x = identity_block(x, 3, [128, 128, 512])
x = identity_block(x, 3, [128, 128, 512])
x = convolutional_block(x, f=3, filters = [256, 256, 1024], s = 2)
x = identity_block(x, 3, [256, 256, 1024])
x = identity_block(x, 3, [256, 256, 1024])
x = identity_block(x, 3, [256, 256, 1024])
x = identity_block(x, 3, [256, 256, 1024])
x = identity_block(x, 3, [256, 256, 1024])
x = convolutional_block(x, f=3, filters = [512, 512, 2048], s = 2)
x = identity_block(x, 3, [512, 512, 2048])
x = identity_block(x, 3, [512, 512, 2048])
x = AveragePooling2D()(x)
x = Flatten()(x)
x = Dense(6, activation='softmax', kernel_initializer = glorot_uniform(seed=1))(x)
model = Model(inputs = x_input, outputs = x)
return model
model = ResNet50()
print(model.summary())