The fitting issue with the Lorentzian plot fitting. On originpro it is fitting good.
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
from lmfit.models import LorentzianModel
import numpy as np
datas = pd.read_csv('pg60_02_0.5V.csv')
a = datas.to_numpy()
a = a.transpose()
x= a[0]
y= a[1]
model = LorentzianModel()
pars = model.guess(y, x=x)
out = model.fit(y, pars, x=x)
print(out.fit_report())
plt.plot(x, y)
plt.plot(x, out.best_fit, '-', label='best fit')
plt.legend()
plt.show()
Here is the Plot.
Related
import matplotlib.pyplot as plt
import pandas as pd
import numpy as np
from scipy import stats
from numpy.linalg import inv
import seaborn as sns
url = r'C:\Users\pchan\kc_house_train_data.csv'
df = pd.read_csv(url,index_col=0)
features_1 = ['sqft_living', 'bedrooms', 'bathrooms', 'lat', 'long']
x=df.filter(features_1)
x = np.c_[np.ones((x.shape[0], 1)), x]
x=pd.DataFrame(x)
y=df.filter(['price'])
y=y.reset_index(drop=True)
x_new=x.T
y.rename(columns = {'price':0}, inplace = True)
w=pd.DataFrame([0]*(x_new.shape[0]))
cost=[]
i=0
a=0.00001
while(i<50):
temp=x.T#(y-x#w)
w=w+(a*temp)
i+=1
print(w)
from sklearn.linear_model import LinearRegression
reg=LinearRegression().fit(x,y)
res=reg.coef_
print(res)
w_closed=np.linalg.inv(x.T#x) # x.T # y
print(w_closed)
Closed Form and Linear Regression from sklearn was able to get correct weights,
But not with gradient descent approach(using Matrix notation).
Whats wrong with Gradient Descent approach here?
I am trying to solve a problem which contains bi-LSTM and CRF, while fitting the model, i am facing this issue ValueError: Failed to convert a NumPy array to a Tensor (Unsupported object type list). Below is the structure of the dataframe.
Columns named "CompanyId" that contains integer. "Name" that contains string. "TableTypeCode" that is a string that is constant and is same as "BS". and final column named "BlockName". I want to train a model using bidirectional lstm and crf . Input being "CompanyId", "Name", and "TableTypeCode" and should predict "BlockName".
import numpy as np
import pandas as pd
df=pd.read_excel("data.xlsx")
from keras.layers import TimeDistributed
from keras.layers import Dense
import pandas as pd
import numpy as np
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
from keras.preprocessing.text import Tokenizer
from keras.utils import to_categorical
from keras.layers import Input, Embedding, LSTM, Dense, TimeDistributed, Bidirectional
from keras.models import Model
!pip install tensorflow-addons==0.16.1
import tensorflow_addons as tfa
X = df[['CompanyId', 'Name', 'TableTypeCode']]
y = df['BlockName']
# Preprocess the data
# One-hot encode the 'CompanyId' and 'TableTypeCode' columns
X = pd.get_dummies(X, columns=['CompanyId', 'TableTypeCode'])
# Tokenize the 'Name' column
X['Name'] = X['Name'].apply(str)
tokenizer = Tokenizer()
X['Name'] = X['Name'].apply(lambda x: x.split())
X['Name'] = tokenizer.texts_to_sequences(X['Name'])
# Encode the target column
encoder = LabelEncoder()
y = encoder.fit_transform(y)
y = to_categorical(y)
# Split the data into training and test sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2)
n_classes = df['BlockName'].nunique()
# Define the model architecture
input_ = Input(shape=(X.shape[1],))
embedding = Embedding(input_dim=X.shape[1], output_dim=50)(input_)
lstm = Bidirectional(LSTM(units=100))(embedding)
output = Dense(n_classes, activation='softmax')(lstm)
model = Model(input_, output)
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
# Train the model
model.fit(X_train, y_train)
There was no issue till the last line of code. Help me fix this and train my model.
I have set up a job lib for parallel computing, so far, I have been able to use it in computing several metrics. I intend to compute g_mean, after the roc_auc. However, I am unable to retrieve y_test and svm_probs from the function. It gives an error when I try to retrieve it.
from sklearn.metrics import roc_auc_score, roc_curve
from sklearn.datasets import make_classification
import pandas as pd
from sklearn.model_selection import KFold
import numpy as np
from sklearn.metrics import classification_report, confusion_matrix, f1_score
from sklearn import svm
from sklearn import datasets
from sklearn.model_selection import StratifiedKFold
from sklearn.svm import LinearSVC
from joblib import Parallel, delayed
from sklearn.datasets import load_breast_cancer
data = load_breast_cancer()
X = data.data
y = data.target
skf = StratifiedKFold(n_splits=5)
clf = svm.SVC(kernel='rbf', probability=True)
def train(train_index, test_index):
X_train, X_test = X[train_index], X[test_index]
y_train, y_test = y[train_index], y[test_index]
clf.fit(X_train, y_train)
r_probs = [0 for _ in range (len(y_test))]
svm_probs = clf.predict_proba(X_test)
svm_probs = svm_probs[:,1]
svm_auc = roc_auc_score(y_test, svm_probs)
return dict(svm_auc=svm_auc)
out = Parallel(n_jobs=2, verbose=100, pre_dispatch='1.5*n_jobs')(
delayed(train)(train_index, test_index) for train_index, test_index in skf.split(X, y))
svm_auc = [d['svm_auc'] for d in out]
print(np.mean(svm_auc))
rf_fpr,rf_tpr, _ = roc_curve(y_test,svm_probs)
gmeans_rf = np.sqrt(rf_tpr * (1-rf_fpr))
ix_rf = np.argmax(gmeans_rf)
print("%.3f" % gmeans_rf[ix_rf])
I'm plotting a function that has several discontinuities. the function is given. I want to connect points with lines only where the function is continuous.
Here is a simplified example of what plot is doing.
import numpy as np
from math import*
import matplotlib.pyplot as plt
from scipy.special import jv, kn
a=sqrt(300-1)
x = np.linspace(0, 0.2, 500)
J0 = jv(0, a*x)
J1 = jv(1, a*x)
K0 = kn(0,x)
K1 = kn(1,x)
Y2=a*x*(J1/J0)
Y3=x*(K1/K0)
plt.xlabel('x')
plt.ylabel('y')
plt.ylim(-10,10)
plt.axhline(0, color='black')
plt.plot(x,Y2)
plt.plot(x,Y3)
plt.show()
After running this code, i get this exception and i didn't found any place to fix it properly
import networkx as nx
from networkx.algorithms import bipartite
import numpy as np
from pandas import DataFrame, concat
import pandas as pd
import matplotlib.pyplot as plt
from scipy.optimize import curve_fit
import ast
import csv
import sys
def plot_degree_dist(G):
in_degrees = G.in_degree()
in_degrees=dict(in_degrees)
in_values = sorted(set(in_degrees.values()))
in_hist = [in_degrees.values().count(x) for x in in_values]
plt.figure()
plt.grid(True)
plt.loglog(in_values, in_hist, 'ro-')
plt.plot(out_values, out_hist, 'bv-')
plt.legend(['In-degree', 'Out-degree'])
plt.xlabel('Degree')
plt.ylabel('Number of nodes')
plt.title('network of places in Cambridge')
#plt.xlim([0, 2*10**2])
I expect to receive a proper graph but all i get is this warning
File "<ipython-input-32-f89b896484d7>", line 2
in_degrees = G.in_degree()
^
IndentationError: expected an indented block
Python relies on proper indentation to identify function blocks. This code should work:
import networkx as nx
from networkx.algorithms import bipartite
import numpy as np
from pandas import DataFrame, concat
import pandas as pd
import matplotlib.pyplot as plt
from scipy.optimize import curve_fit
import ast
import csv
import sys
def plot_degree_dist(G):
in_degrees = G.in_degree()
in_degrees=dict(in_degrees)
in_values = sorted(set(in_degrees.values()))
in_hist = [in_degrees.values().count(x) for x in in_values]
plt.figure()
plt.grid(True)
plt.loglog(in_values, in_hist, 'ro-')
plt.plot(out_values, out_hist, 'bv-')
plt.legend(['In-degree', 'Out-degree'])
plt.xlabel('Degree')
plt.ylabel('Number of nodes')
plt.title('network of places in Cambridge')
#plt.xlim([0, 2*10**2])
Basically just indent it by 2 or 4 spaces as per your style requirements.