Basic data analysis and predictions

[jefsummers]

Spent some time on this tonight. Note that in my version I read the csv differently, from a different source (my Google drive). It still has errors, but the plot at the end shows the modeled values - next step is to plot the actual vs the modeled, and do stats on them if you want

# Load libraries
from pandas import read_csv
from pandas.plotting import scatter_matrix
from matplotlib import pyplot
from sklearn.model_selection import train_test_split
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import StratifiedKFold
from sklearn.metrics import classification_report
from sklearn.metrics import confusion_matrix
from sklearn.metrics import accuracy_score
from sklearn.linear_model import LogisticRegression
from sklearn.tree import DecisionTreeClassifier
from sklearn.neighbors import KNeighborsClassifier
from sklearn.discriminant_analysis import LinearDiscriminantAnalysis
from sklearn.naive_bayes import GaussianNB
from sklearn.svm import SVC
import pandas as pd
from sklearn.preprocessing import PolynomialFeatures
from sklearn.linear_model import LinearRegression
import matplotlib.pyplot as plt
from sklearn.linear_model import LinearRegression

# Load dataset
from google.colab import drive
drive.mount('/content/drive')
filename = (r'/content/drive/My Drive/analyza_casovych_radov.csv')
cols = ['Rok', 'Pocet prepravenych cestujucich', ]
dataset = pd.read_csv(filename, names=cols)
df = dataset

trainval_dataset = df.sample(frac=0.8,random_state=42)
test_dataset = df.drop(trainval_dataset.index)
train_dataset = trainval_dataset.sample(frac=0.8, random_state=42)
validate_dataset = trainval_dataset.drop(train_dataset.index)
print ()
print(f"Train {train_dataset.shape} Validate {validate_dataset.shape} Test {test_dataset.shape}")

print ()
print ()

print ('train_dataset= ')  
print (train_dataset)

print ()
print ('test_dataset= ')  
print (test_dataset)

print ()
print ('validate_dataset= ')
print (validate_dataset)

print()

X = train_dataset['Rok']
y = train_dataset['Pocet prepravenych cestujucich']


poly = PolynomialFeatures(2)

X_poly = poly.fit_transform(X.to_frame().values.reshape(-1, 1))
poly.fit(X_poly, y) 
lin2 = LinearRegression() 
lin2.fit(X_poly, y) 

plt.scatter(X.values, y, color = 'blue') 
  
plt.plot(X.values, lin2.predict(poly.fit_transform(X_poly)), color = 'red') 
plt.title('Polynomial Regression') 
plt.xlabel('Rok') 
plt.ylabel('Other') 
  
plt.show()
#print (poly.fit_transform(X))

#plt.scatter(X, y, color = 'blue')
#plt.plot(X, (poly.fit_transform(X)), color = 'red')
#plt.show()

Output:
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
<ipython-input-20-b5736948e378> in <module>()
     64 plt.scatter(X.values, y, color = 'blue')
     65 
---> 66 plt.plot(X.values, lin2.predict(poly.fit_transform(X_poly)), color = 'red')
     67 plt.title('Polynomial Regression')
     68 plt.xlabel('Rok')

2 frames
/usr/local/lib/python3.6/dist-packages/sklearn/utils/extmath.py in safe_sparse_dot(a, b, dense_output)
    149             ret = np.dot(a, b)
    150     else:
--> 151         ret = a @ b
    152 
    153     if (sparse.issparse(a) and sparse.issparse(b)

ValueError: matmul: Input operand 1 has a mismatch in its core dimension 0, with gufunc signature (n?,k),(k,m?)->(n?,m?) (size 3 is different from 10)