def month_by_month():
"""Creates line plot of expenses per month. Can be filtered by either type of payment, expense or both"""
exp = str(cat.get()) #gets value of expense filter from GUI
payment = str(pay.get())# gets value of payment filter from GUI
months = []
amounts = []
for month in range(1,13):
df_month = df[df['Month']==month]
update_filts(df_month) #updates filters for monthly dataframe
filt = exp_filters[exp]|pay_filters[payment] # combines boolean filters selecting only wanted values
months.append(month)
amounts.append(df_month[filt]['Amount'].sum()) # sums all values from 'Amount' column from filtered dataframe
plt.plot(months,amounts)
plt.title(('{} Expenses Using {} Payment Method').format(exp,payment))
plt.xtitle('Month')
plt.ytitle('Amount Spent')
update_filts() #resets filters to values from main dataframe
plt.show()
def seaborn_charts(df):
bar_plot = sns.barplot(data=df,
x="col_name",
y="col_name",
style="summer",
hue="summer")
# to set/reset x, y & title axes names
plot.xtitle("x title")
plot.ytitle("y title")
plot.title("my title")
scatter_plot = sns.scatterplot(data=df, x="", y="")
line_plot = sns.lineplot(data=df, x="", y=["", ""])
count_plot = sns.countplot(data=df, x="")
heat_map = sns.heatmap(data=["some_list"], cmap=["yellow", "red"])
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
dataset = pd.read_csv(' ')
X = dataset.iloc[:, ].values
y = dataset.iloc[:, ].values
# Fitting the Regression model to dataset
# Predicting the result of the Regression model
y_pred = regressor.predict()
# Visualising the results of the Regression model
plt.scatter(X, y, color='red')
plt.plot(X, predict(X), color='blue')
plt.xtitle('')
plt.xlabel('')
plt.ylabel('')
plt.show()
# Visualising the results of the Regression model (for high resolution and smoother curve)
X_grid = np.arange(min(X), max(X), 0.1)
X_grid = np.reshape(len(X_grid), 1)
plt.scatter(X, y, color='red')
plt.plot(X_grid, predict(X_grid), color='blue')
plt.xtitle('')
plt.xlabel('')
plt.ylabel('')
plt.show
# Hierarchical Clustering
# import libraries
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
# importing dataset
dataset = pd.read_csv('Mall_Customers.csv')
X = dataset.iloc[:,3:].values
# using dendrograms to determine the optimal number of clusters
import scipy.cluster.hierarchy as sch
dendrogram = sch.dendrogram(sch.linkage(X , method = 'ward'))
plt.title('Dendrogram')
plt.xtitle('Customers')
plt.ytitle('Euclidean Distance')
plt.show()
# fitting Hierarchical Clustering Algorithm to the dataset
from sklearn.cluster import AgglomerativeClustering
hc = AgglomerativeClustering(n_clusters = 5, affinity = 'euclidean', linkage = 'ward')
y_hc = hc.fit_predict(X)
# visualising HC
plt.scatter(X[y_hc == 0,0], X[y_hc == 0,1], s =100, c = 'red' , label = 'Cluster - 1' )
plt.scatter(X[y_hc == 1,0], X[y_hc == 1,1], s =100, c = 'yellow' , label = 'Cluster - 2' )
plt.scatter(X[y_hc == 2,0], X[y_hc == 2,1], s =100, c = 'black' , label = 'Cluster - 3' )
plt.scatter(X[y_hc == 3,0], X[y_hc == 3,1], s =100, c = 'orange' , label = 'Cluster - 4' )
plt.scatter(X[y_hc == 4,0], X[y_hc == 4,1], s =100, c = 'blue' , label = 'Cluster - 5' )
plt.xlabel('Annual Income - k$')
#plt.hist(sector_consistency_temp['degree'],bins=30)
### Most consistent stocks per threshold\
l = {}
overlap = pd.DataFrame(np.zeros((Betas.shape[0], len(thres_array))),
index=Betas.index,
columns=thres_array)
for thres in thres_array:
l[thres] = consistency[thres][
consistency[thres].argsort() > Betas.shape[0] - 200]
overlap.loc[l.index, thres] += 1
plt.figure()
for d in [0, 1, 2, 4, 5, 10]:
plt.plot(thres_array, [np.sum(degree[t] == 0) for t in thres_array],
label=d)
plt.xtitle('threshold for the correlation')
plt.ytitle('proportion of nodes with given degree')
plt.title('Evolution of the degree with the threshold value')
plt.legend(loc='upper left')
plt.show()
#### Decomposition in the eigenvalue sapce
import pygsp
Gg = pygsp.graphs.Graph(cor_res)
Gg.compute_fourier_basis()
D = np.zeros(Gg.N)
D[:5] = Gg.e[:5]
D = np.diag(D)
Alt = Gg.U * D * U.T
#### Definition of a sufficient statisitic
### Distances between matrices
T = np.array([[1,0],
[1,0],
[1,0],
[1,0],
[1,0],
[0,1],
[0,1],
[0,1],
[0,1],
[0,1]])
#-------------------------------------------
plt.scatter(X[:,0], X[:,1])
plt.title('Datos para ajustar ELM')
plt.xtitle('X')
plt.ytitle('Y')
plt.show()
#-------------------------------------------
L = 70 # numero de capas ocultas 5e06 no puede operar
N,d = X.shape
m = T.shape[1]
a, b = generar_a_b(d,L)
#print("Dimension a: ",a.shape)
H, H_tr = generar_H(a,b,X,N,L)
C = .10
beta = []
# Version cuando N grande
classifier_2 = KNeighborsClassifier(n_neighbors=28, metric='minkowski', p=2)
classifier_2.fit(X_train, y_train)
y_pred_2 = classifier_2.predict(X_test)
Cm_3 = metrics.classification_report(y_test, y_pred_2)
Cm_4 = metrics.accuracy_score(y_test, y_pred_2)
from sklearn.metrics import roc_curve, auc
y_pred_proba = classifier.predict_proba(X_train)[:, 1]
fpr, tpr, threshold = roc_curve(y_train, y_pred_proba)
auc_logit = auc(y_train, y_pred_proba)
plt.figure(figsize=(5, 5), dpi=100)
plt.plot(fpr, tpr, linestyle='-')
plt.xtitle("False Positive Rate")
plt.ytitle("True Positive Rate")
from sklearn.datasets.samples_generator import make_blobs
from matplotlib.colors import ListedColormap
X_train, y_train = make_blobs(n_samples=100,
centers=2,
random_state=0,
cluster_std=0.60)
for i, j in enumerate(np.unique(y_train)):
plt.scatter(X_train[y_train == j, 0],
X_train[y_train == j, 1],
c=ListedColormap(('red', 'green'))(i),
s=50,
cmap='autumn',
label=j)