def read_css():
"""I may never have written a more painful function in my life.
If you want data, and are thinking of using numpy or pandas --
read it in by hand.
"""
# Can't delete array elements.
#ix = 1 #so as to skip the header row.
n = 21
chunk = 2*n + 3 # Both matrices, and 3 extra rows
advice = np.zeros((n, n, n))
friendship = np.zeros((n, n, n))
pdf = pd.read_csv("/Users/alexloewi/Documents/Data/cognitive social structures/rearranged_cogsocstr.txt", sep="\t")
matrix_columns = pdf[pdf.columns[0:21]]
#print 'matrix columns!!!!!!,', matrix_columns
for perceiver in range(n):
# This gets all the data for one person
x = (chunk*perceiver)
y = (chunk*(perceiver+1))-1
a = np.array(matrix_columns.ix[x:x+20])
np.fill_diagonal(a, 0)
f = np.array(matrix_columns.ix[x+21:x+41])
np.fill_diagonal(f, 0)
advice[perceiver,:,:] = a #np.array(matrix_columns.ix[0:20])
friendship[perceiver,:,:] = f #np.array(matrix_columns.ix[21:41])
# Consensus matrices (AND rule)
ca = np.zeros((n,n))
cf = np.zeros((n,n))
for i,j in np.ndindex(ca.shape):
if advice[i,i,j] + advice[j,i,j] == 2:
ca[i,j] = 1
for i,j in np.ndindex(cf.shape):
if friendship[i,i,j] + friendship[j,i,j] == 2:
cf[i,j] = 1
# Self-proclaimed relationships (OR rule)
sa = np.zeros((n,n))
sf = np.zeros((n,n))
for i,j in np.ndindex(sa.shape):
if advice[i,i,j] + advice[j,i,j] >= 1:
sa[i,j] = 1
for i,j in np.ndindex(sf.shape):
if friendship[i,i,j] + friendship[j,i,j] >= 1:
sf[i,j] = 1
return advice, friendship, ca, cf, sa, sf
def _readData(self, filePath):
df = pd.read_csv(filePath)
if self.config.numClasses == 1:
labels = df["sentiment"].tolist()
elif self.config.numClasses > 1:
labels = df["rate"].tolist()
review = df["review"].tolist()
reviews = [line.strip().split() for line in review]
return reviews, labels
def sensores():
lista = []
df = pd.read_csv("../mqtt/test/log.csv")
tamanho = len(df)
dado = (np.array(df[tamanho - 5:tamanho]).tolist())
n_dado = []
for i in range(len(dado)):
#for j in range(len(dado[i])):
n_dado = "IoT ID: %s\nMES: %s\nDIA: %s\nHora: %s\nUmidade: %s\n*************" % (
dado[i][0], dado[i][1], dado[i][2], dado[i][3], dado[i][4])
lista.append(n_dado)
#print lista
return lista
def load_data(cat_filename):
"""Loads a given number of rows from catalog and return test and train"""
# load catalog data, convert the data in to a function so that we can process it
cat_data = pd.read_csv(cat_filename,
delim_whitespace=True,
comment='#',
header=None)
# give column names
cat_data.columns = ['id','redshift','tu','tg','tr','ti','tz','ty',\
'u10','uerr10','g10','gerr10','r10','rerr10',\
'i10','ierr10','z10','zerr10','y10','yerr10']
return cat_data
def read(self):
try:
if len(file_csv) == 1:
self._rows = csv.DictReader(open(self.csv_file))
else:
# Use PD
df_merged = pd.concat(
[pd.read_csv(f, sep=',') for f in self.csv_file],
ignore_index=True,
sort=False)
self._rows = df_merged
except Exception as ERR:
print('[CRITICAL] ' + str(ERR))
def readDataFrame(filepath):
df = pd.read_csv(filepath)
# The last column should be the labels, which leaves an even number of columns.
nb_col = len(df.columns)
mid = (nb_col - 1) / 2
Y = df[-1] # Interacts or not ? Labels
X1 = df[1:mid] # First protein representations
X2 = df[mid:-1] # Second protein representations
# The respective order of the labels MUST be conserved
# Reshape with numpy !
# Data must be converted into a vector processable by sklearn
# Based on what I've read on conjoined triads, it should be the case already.
return (X1, X2, Y)
def height(carats, height_range, vec, min_height, safety_step):
df = pd.read_csv(carats, names = ('time', 'airplanename', 'y','x','z','keisiki'))
plane_list = list(df['airplanename'])
plane_name = list(set(plane_list))
listed_data = []
for p in plane_name:
plane_sort = df[df['airplanename'] == p]
plane_sort = plane.sort_values(by = ["time"], ascending = True)
i1 = None
i2 = None
rows = []
for i, row in plane_sort.iterrows():
rows.append(row)
for i in range(safety_step*2):
if i >= lne(rows):
break
row = rows[i]
judge = False
listed_data.append(list(row)+[judge])
for i in range(safety_step*2, len(rows)):
row = rows[i]
i1 = rows[i-safety_step]
i2 = rows[i-safety_step * 2]
ii = row
judge = True
if not (abs(ii[]'z'] - i1['z']) < height_range and abs(ii['z'] - i2['z']) < height_range):
judge = False
else:
v1 = cp.vector(i1['x'] - i2['x'], i1['y']-i2['y'])
v2 = cp.vector(ii['x'] - i1['x'], i1['y']-i1['y'])
v1.normalization()
v2.normalization()
dot = v1.dot(v2)
if vec >= dot:
judge = False
elif ii['z'] <= min__height:
judge = False
listed_data.append(list(row) + [judge])
def __init__(self, data_path, learning_rate=0.001, reward_decay=0.9, e_greedy=0.9):
self.learning_rate = learning_rate
self.gamma = reward_decay
self.features = pd.read_csv(data_path, sep=',')#need preprocess
self.epsilon = e_greedy
self.step_index = 0
self.cost = []
self.memory_count = 0
self.INITIAL_EPSILION = e_greedy
self.FINAL_EPSILON = 0.01
self.BATCHSIZE = 20
self.EXPLORE = 300000
self.OBSERVE = 1000
self.MAXSTEP = 100000
self.MAXSIZE = 9000
self.DEPTH = 3
self.replay_buffer = deque()
self.q_table[0] = pd.Dataframe()
self.q_table[1] = pd.Dataframe()
def load_sp500(input_size,
num_steps,
k=None,
target_symbol=None,
test_ratio=0.05):
if target_symbol is not None:
return [
StockDataSet(target_symbol,
input_size=input_size,
num_steps=num_steps,
test_ratio=test_ratio)
]
# Load metadata of s & p 500 stocks
info = pd.read_csv(
"data/constituents-financials.csv") #must prepare a sp 500 file
info = info.rename(
columns={col: col.lower().replace(' ', '_')
for col in info.columns})
info['file_exists'] = info['symbol'].map(
lambda x: os.path.exists("data/{}.csv".format(x)))
print(info['file_exists'].value_counts().to_dict())
info = info[info['file_exists'] == True].reset_index(drop=True)
info = info.sort('market_cap', ascending=False).reset_index(drop=True)
if k is not None:
info = info.head(k)
print("Head of S&P 500 info:\n", info.head())
# Generate embedding meta file
info[['symbol', 'sector']].to_csv(os.path.join("logs/metadata.tsv"),
sep='\t',
index=False)
return [
StockDataSet(row['symbol'],
input_size=input_size,
num_steps=num_steps,
test_ratio=0.05) for _, row in info.iterrows()
]
def k_means_pp(...):
np.random.seed(0)
args=command_line_arg()
K,N,d,MAX_ITER,filename=args.K, args.N, args.d,args.MAX_ITER, args.filename
observation_file=pd.read_csv(filename)
observation_file=observation_file.values.tolist()
observation_list=[]
for x in observation_file:
obs=observation(x)
observation_list.append(obs)
found_centroid=[]
#step 1 - choose random M
first_seed=np.random(N,1);
if(first_seed==1):
return 1
else:
for j in range(2,K):
found_centroid.append(observation_list[first_seed])
calculate_d(found_centroid, observation_list)
p_vector=create_p_vector(observation_list)
first_seed=np.random(N,1,p_vector)
if(len(found_centroid))
import panda as pd data_infile = '../40-pn-dataset-auto.csv' data = pd.read_csv(data_infile)
# -*- coding:utf-8 -*- # /usr/bin/python ''' Author:Yan Errol Email:[email protected] Wechat:qq260187357 Date:2019-05-13--11:26 File： Describe: 数据相关性分析， ''' print(__doc__) import panda as pd # Step 0 - Read the dataset, calculate column correlations and make a seaborn heatmap data = pd.read_csv( 'https://raw.githubusercontent.com/drazenz/heatmap/master/autos.clean.csv') corr = data.corr() ax = sns.heatmap(corr, vmin=-1, vmax=1, center=0, cmap=sns.diverging_palette(20, 220, n=200), square=True) ax.set_xticklabels(ax.get_xticklabels(), rotation=45, horizontalalignment='right')
import panda
data1 = panda.read_csv('/home/rikesh/Citytech/Self/test/test.json', sep="\t")
print(data1)
def textprocessing():
commentList = []
dateList = []
for i in range(10):
num = i + 1
[commentList_temp, dateList_temp] = getComments(num)
commentList.append(commentList_temp)
dateList.append(dateList_temp)
commentList = reduce(operator.add, commentList)
dateList = reduce(operator.add, dateList)
dataTmp = {'comments': commentList[:], 'date': dateList[:]}
df2 = pd.DataFrame(dataTmp)
pd.DataFrame(df2).to_excel("text-movie.xls",
sheet_name="sheet1",
index=False,
header=True)
comments = ''
for k in range(len(commentList)):
comments = comments + (str(commentList[k])).strip()
pattern = re.compile(r'[\u4e00-\u9fa5]+')
filterdata = re.findall(pattern, comments) # 过滤标点 用正则表达式
cleaned_comments = ''.join(filterdata)
seg_list_exact = jieba.cut(cleaned_comments, cut_all=False) # 精确模式分词
object_list = []
remove_words = pd.read_csv("stopwords.txt",
index_col=False,
quoting=3,
sep="\t",
names=['stopword'],
encoding='utf-8')
for word in seg_list_exact: # 循环读出每个分词
if word not in remove_words: # 如果不在去除词库中
object_list.append(word) # 分词追加到列表
# 词频统计
word_counts = collections.Counter(object_list) # 对分词做词频统计
word_counts_top10 = word_counts.most_common(10) # 获取前10最高频的词
print(word_counts_top10) # 输出检查
# 词频展示
mask = np.array(Image.open('background.jpg')) # 定义词频背景
wc = wordcloud.WordCloud(
background_color='white', # 设置背景颜色
font_path='/System/Library/Fonts/Hiragino Sans GB.ttc', # 设置字体格式
mask=mask, # 设置背景图
max_words=200, # 最多显示词数
max_font_size=100, # 字体最大值
scale=32 # 调整图片清晰度，值越大越清楚
)
wc.generate_from_frequencies(word_counts) # 从字典生成词云
image_colors = wordcloud.ImageColorGenerator(mask) # 从背景图建立颜色方案
wc.recolor(color_func=image_colors) # 将词云颜色设置为背景图方案
wc.to_file("/Users/ownpro/Desktop/temp.jpg") # 将图片输出为文件
plt.imshow(wc) # 显示词云
plt.axis('off') # 关闭坐标轴
plt.show() # 显示图像
import panda as pd
df = pd.read_csv('pokemon.csv')
print(df.head(3)
print(df.tail(3)
df1 = pd.read_excel('pokemen.excel')
print(df.columns) // headers
df['name']
df['name','type]
df.iloc[1:4] // rows from 1 to 4
df.iloc[2,1] // second row first position
for index,row in df.iterrows():
print(index,row) // show rows by index
for index,row in df.iterrows():
print(index,row['Name'] // show name columns
df.loc[df['type 1] == 'fire'] //finding specific textual information
df.describe() //mean and different stats
df.sort_values('name') // sort values by name
df.sort_values([name', 'hp'], ascending= False) // sort values by two columns
import numpy as np
import panda as pa
import matplotlib.pyplot as plt
plt.rcParams['figure.figsize'] = (20.0, 10.0)
data = pa.read_csv('headerbrain.csv')
print(data.shape)
data.head()
import panda as pd
pd.read_csv("../data/gapminder.tsv, sep = '\t') #rea the csv using the Tab separator
def clear_na_from_csv(csv_source, csv_dest):
existing_csv = pd.read_csv(csv_source)
csv_without_na = existing_csv.dropna()
csv_without_na.to_csv(csv_dest)
y_pred_f = K.flatten(y_pred)
intersection = K.sum(y_true_f * y_pred_f)
score = (2. * intersection + smooth) / (K.sum(y_true_f) + K.sum(y_pred_f) + smooth)
return score
def dice_loss(y_true, y_pred):
loss = 1 - dice_coeff(y_true, y_pred)
return loss
def bce_dice_loss(y_true, y_pred):
loss = binary_crossentropy(y_true, y_pred) + dice_loss(y_true, y_pred)
return loss
### Load Data ###
### Read CSV
df_trn_val = pd.read_csv('Kaggle_Car_Data/train/train_masks.csv')
### Extract IDs
ids_trn_val = df_trn_val['img'].map(lambda s: s.split('.')[0])
### Train Data IDs and Validation Data IDs
ids_train_split, ids_valid_split = train_test_split(ids_trn_val, test_size = 0.2, random_state = 42)
print('Training on {} samples'.format(len(ids_train_split)))
print('Validating on {} samples'.format(len(ids_valid_split)))
### 4070 vs. 1018
### Paths
kaggle_train_path = 'Kaggle_Car_Data/train/train'
kaggle_train_mask_path = 'Kaggle_Car_Data/train_masks/train_masks'
kaggle_test_path = 'Kaggle_Car_Data/test/test'
import panda as pd
import numpy as np
from sklearn.feature_extraction.text import CounterVectorizer
from sklearn.metrics.pairwise import Cousine_simlarity
def get_title_from_index(index):
return df[df.index == index]["title"].values[0]
def get_title_from_index(index):
return df[df.title == title]["index"].values[0]
df = pd.read_csv("")
features = ['keywords','cast','genres','director']
for feature in features:
df[feature] = df[feature].fillna('')
def combine_features(row):
try:
return row['keywords']+" "+row['cast']+" "+row['genres']+" "+row['director']
except:
print("Error", row)
df["combined_features"] = df.apply(combine_features,axis=1)
#print(df["combined_features"].head())
cv = CountVectorizer()
count_matrix = cv.fit_transform(df["combined_features"])
cosine_simi = cosine_similarity(count_matrix)
from time import sleep
from selenium import webdriver
from webdriver_manager.chrome import ChromeDriverManager
from selenium.webdriver.chrome.options import Options
from bs4 import BeautifulSoup
import panda as pd
df = pd.read_csv("https://covid19.who.int/WHO-COVID-19-global-table-data.csv")
df = df.drop([
'WHO Region', 'Cases - cumulative total per 100000 population',
'Cases - newly reported in last 7 days per 100000 population',
'Deaths - cumulative total per 100000 population',
'Deaths - newly reported in last 7 days',
'Deaths - newly reported in last 7 days per 100000 population',
'Transmission Classification'
],
axis=1)
df = df.set_index('Name')
df['Recovered'] = df['Cases - cumulative total'] - df[
'Deaths - cumulative total']
df = df.drop(
['Cases - cumulative total', 'Deaths - newly reported in last 24 hours'],
axis=1)
inp = input("Digite o país: ")
df.loc[[inp]]
import matplotlib.pyplot as plt
recovered = df.at[inp, 'Recovered']
Deaths = df.at[inp, 'Deaths - cumulative total']
'''Intro to ML'''
import panda as pd
# read data and store data in DF
data = pd.read_csv(csv_file_path, index_col='Id')
# print a summary statistics of data
data.describe()
# prints the first couple of row of data
data.head()
# print list of columns in the dataset
data.columns
# drops missing values
data.dropna(axis=0)
# selecting prediction target with dot-notation -- stored as Series
y = data.Target
# selecting features with a column list
features = ['f_1', 'f_2', ...]
X = data[features]
'''Build ml models with scikit-learn (sklearn) for DF data
0) Split training data into training and validation data
- the validation data measures the model's accuracy
- once a model is selected, predict on testing data
1) Define the model
2) Fit model to make prediction
import panda as pd
dataset = pd.read_csv('225245.csv')
import panda as pd
df = pd.read_csv("temperatures.csv")
df.head(2) #(2) stands for how many rows you want it to show
df.head() # shows only the head list
df.tail() #
df.values
df["temperature"]
df["day"].head()
df["temperature"] > 20 # shows all the temperatures below 20 degrees from the temperatures.csv file
df["temperature"] < 0 # shows all the temperatures below 0 degrees from the file
df_cool = df[df["temperature"] < 0]
df_cool.head()
df_cool.to_csv("cool.csv") # saves a new csv file named cool.csv
#save stuff into a new file
df["temperature"].mean() # this shows the average
df["temperature"].max() # this shows the maximum temperature
df["temperature"].min() # this shows the minimum temperature
df["temperature"].value_counts(
) # it counts how many times a certain value occurs in a row/list
df["temperature"].value_counts().head()
snacks = pd.Series(["Mars", "Twix", "Oreo"])
import panda as pd
df = pd.read_csv('C:/Users/iamay/Desktop/PY/data/iris.csv')
x = df['Species']
x.unique()
a = list(x)
import panda as pd
from gensim.models import Word2Vec
import gensim, logging
logging.basicConfig(format='%(asctime)s : %(levelname)s : %(message)s', level=logging.INFO)
# w2v预训练
data=pd.read_csv('../user_data/tmp_data/all_data_txt.txt',header=None)
w2v=Word2Vec(data[0].apply(lambda x:x.split(' ')).tolist(),size=128, window=8, iter=50, min_count=2,
sg=1, sample=0.002, workers=6 , seed=1018)
# 保存模型
w2v.wv.save_word2vec_format('../user_data/pretraining_model/w2v_128.txt')
## transfomer预训练-----------------------
from transformers import BertTokenizer, WEIGHTS_NAME,TrainingArguments
from model.modeling_nezha import NeZhaForSequenceClassification,NeZhaForMaskedLM
from model.configuration_nezha import NeZhaConfig
import tokenizers
from datasets import load_dataset,Dataset
from transformers import (
CONFIG_MAPPING,
MODEL_FOR_MASKED_LM_MAPPING,
AutoConfig,
AutoModelForMaskedLM,
AutoTokenizer,
DataCollatorForLanguageModeling,
HfArgumentParser,
Trainer,
TrainingArguments,
set_seed,
#importing required libraries
from sklearn.cluster import KMeans
import panda as pd
from numpy np
from collections import Counter
import csv
import os
from sklearn.preprocessing import StandardScaler
import matplotlib.pyplot as plt
#reading dataset
data = pd.read_csv('/root/task5/pro.csv')
#dropping the unusefull
data = data.dropna()
data = data.drop(['url'], axis='columns',implace=True)
ip= data['IP']
count=Counter(ip)
#scalling the dataset
sc = StandardScaler()
data_scaled = sc.fit_transform(dataset)
model = KMeans(n_clusters=4)
#fitting the model
model.fit(data_scaled)
pred = model.fit_predict(data_scaled)
dataset_scaled = pd.DataFrame(data_scaled, columns=['IP', 'c'])
pred=dataset_scaled['cluster']
#plotting the clusters
f1 = data[data.cluster==0]
f2 = data[data.cluster==1]
# IMPORTING LIBRARIES
import panda as pd
import numpy as np
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
df = pd.read_csv('california_housing_test')
df.head()
y = df['total_rooms']
x = df[['longitude', 'latitude', 'housing_median_age']]
def CasesReg(x, y):
from sklearn.linear_model import LinearRegression
reg = LinearRegression()
reg.fit(x, y)
return reg
x_train, x_test, y_train, y_test = model_selection.train_test_split(x, y)
reg = CasesReg(x_train, y_train)
y_pred = reg.predict(x_test)
y_pred
reg.score(x_test, y_test)
plt.plot(x, reg.predict(x), '*')
plt.legend(labels=['longitude', 'latitude', 'housing_median_age'])
# import panda as pd import numpy as np # read in data train = pd.read_csv()
### Code doesn't execute as given
import panda as pd ### You mean pandas?
import numpy as np
import matplotlib
from matplotlib import pyplot as plt
votes = []
for line in open ("ELECTION_ID"):
year = line.split(" ")[0]
header = pd.read_csv(year + ".csv", nrows = 1).dropna(axis = 1)
d = header.iloc[0].to_dict()
### The following line can't even be executed
df = pd.read_csv(year+".csv", index_col = 0,thousands = ",", skiprows = [1])
df.rename(inplace = True, columns = d)
df.dropna(inplace = True, axis = 1)
df["Year"] = 2004
votes.append(df)
for year in range(len(votes)):
majorVote = pd.concat([votes[year][['Democratic','Republican','Total Votes Cast','Year']]], axis = 1).head(1)
majorVote['Republican Vote Share'] = majorVote['Republican']/majorVote['Total Votes Cast']
if year == 0:
voteShare = pd.concat([majorVote], axis = 1)
else:
voteShare = pd.concat([voteShare, majorVote], axis = 0)
ax = voteShare.plot(x = 'Year', y = "Republican Vote Share", \
title = "President General Election Results in Accomack County, Virginia")
import panda as pd
import sklearn
# read in dataset
data = pd.read_csv('Dateset.csv')
data.head()
# create an indicator column for overpayment
data['Overpayment_ind'] = (data.Overpayment_Amount != ' ').astype(int)
data.columns
# construct and design matrix
from patsy import dmatrices
y, X = dmatrices('Overpayment_ind ~ Age_in_yrs + Income + \
Rent_Amount + Number_Children + C(Moved_from_out_of_state_12_mths) + \
C(Citizenship) + C(Previous_Felony)',
data, return_type='dataframe')
print X.columns
# rename indicator columns to a mroe readable form
X = X.rename(columns = {'C(Moved_from_out_of_state_12_mths)[T.Y]':'Moved_from_out_of_state_12_mths',
'C(Citizenship)[T.Verified]':'Citizenship_Verified',
'C(Previous_Felony)[T.Y]':'Previous_Felony'})
X.head()
import numpy as np
from sklearn.linear_model import LogisticRegression
ya = np.ravel(y)
model = LogisticRegression()
model = model.fit(X,ya)
from tensorflow.keras.layers import Dense #Dense Layer
from tensorflow.keras.models import Sequential #whatever we do to the model will happen in sequence
import panda as pd # can call panda as pd in my code
#get data
data = pd.read_csv('linear.csv', header=0, index_col=0)
#print(data.head()) #verify and make sure it's printing the correct info
indicies = data.index.values
#print(indices)
values = data['value'.values] #we want the column value and its values
print(values)
model = Sequential()
model.add(Dense(8, input_shape=(1, ))) #adding a layer (input + hidden)
#8= nodes , (1, TBD (however many rows))
model.add(Dense(32))
#add another layer with 32 nodes. Grabs the shape of the previous layer
#LSTM - model that allows you to pass in states...
model.add(Dense(1))
#OUTPUT LAYER = number of predictions you want
model.compile(optimizer ='adam', loss='mae')
#compile the model. can add optimizer(adam- minimizes errors) and loss function (mae - Mean absolute error)
model.fit(indicies, values, epochs=1, batch_size=1)
#epochs = 1 iteration through the entire data set
#batch size - send 1 data at a time and update your weights
import panda as pd
from keras.models import Sequential
from keras.layers import Dense, Dropout
previsores = pd.read_csv('entradas-breast.csv')
classe = pd.read_csv('saidas-breast.csv')
classificador = Sequential()
classificador.add(
Dense(units=8,
activation='relu',
kernel_initializer='normal',
input_dim=30))
classificador.add(Dropout(0.2))
classificador.add(
Dense(units=8, activation='relu', kernel_initializer='normal'))
classificador.add(Dropout(0.2))
classificador.add(Dense(units=1, activation='sigmoid'))
classificador.compile(optimizer='adam',
loss='binary_crossentropy',
metrics=['binary_accuracy'])
classificador.fit(previsores, classe, batch_size=10, epochs=100)
classificador_json = classificador.to_json()
with open('classificador_breast.json', 'w') as json_file:
json_file.write(classificador_json)
classificador.save_weights('classificador_breast.h5')
import panda as pd
import numpy as np
from sklearn.linear_model import LogisticRegression
from sklearn.model_selection import train_test_split
from sklearn.metrics import accuracy_score
# Load the dataset
default = pd.read_csv('default.csv')
# Inspect the dataset
default.head()
# Convert the student attribute into dummy variables 0s and 1s
default = pd.get_dummies(default, drop_first=True)
# Set the RNG seed so that we get reproducible results
# Splitting is random process
# Seed value doesn't really matter
np.random.seed(0)
# Grab our input and output data
x_data = default[default.columns.difference(['default'])]
y_data = default['default']
# We can now split this into training and testing sets
x_train, x_test, y_train, y_test = train_test_split(x_data, y_data, test_size=0.3)
# Initialize the model without changing any of the default parameters
model = LogisticRegression()
# Fit the model on our training data
mat[3:5,:]
.sum() #Get the sum of all the values in mat
.std() #get the standard deviation of the values in mat
.sum(axis=0) #Get the sum of all the columns in mat
.sqrt(arr) .mean() .min() .max() .count()
.exp(arr) .describe() .transpose() .info()
.sin(arr)
.log(arr)
NP can do regular operation * / + - < > <= >= !=
Pandas use to convert different type data to table and use advance function to filter and remap the data
import panda as pd
#read and write to csv file
df = pd.read_csv('file_name')
df = df.to_csv('example', index=False)
#Excel Input and output, beware of image in the excel file, it may cause it to crash
pd.read_excel('Excel_Sample.xlsx',sheetname='Sheet1')
pd.to_excel('excelname.xlsm', sheetname)
#Html Input
df = pd.read_html('http://.....html')
#Read Database in sql
from sqlalchemy import create_engine
engine = create_engine('sqlite:///:momory:')
df.to_sql('data', engine)
sql_df = pd.read_sql('data', con=engine)
#Convert to DataFrames
df= pd.DataFrame(np.random(5,4), index='A B C D E'.split(), columns='W X Y Z'.split())
df['W'] or df['W', 'Z'] #to call one or more column
