Windows commits

Salary_Data.csv

@@ -0,0 +1,31 @@
+YearsExperience,Salary
+1.1,39343.00
+1.3,46205.00
+1.5,37731.00
+2.0,43525.00
+2.2,39891.00
+2.9,56642.00
+3.0,60150.00
+3.2,54445.00
+3.2,64445.00
+3.7,57189.00
+3.9,63218.00
+4.0,55794.00
+4.0,56957.00
+4.1,57081.00
+4.5,61111.00
+4.9,67938.00
+5.1,66029.00
+5.3,83088.00
+5.9,81363.00
+6.0,93940.00
+6.8,91738.00
+7.1,98273.00
+7.9,101302.00
+8.2,113812.00
+8.7,109431.00
+9.0,105582.00
+9.5,116969.00
+9.6,112635.00
+10.3,122391.00
+10.5,121872.00

TurkeyData.csv

@@ -0,0 +1,46 @@
+observation_date,ECOMSA
+2011-01-01,9668.86
+2011-04-01,10795.59
+2011-07-01,12959.36
+2011-10-01,11680.76
+2012-01-01,13919.98
+2012-04-01,14334.31
+2012-07-01,16510.52
+2012-10-01,15500.27
+2013-01-01,15993.59
+2013-04-01,15956.83
+2013-07-01,19535.96
+2013-10-01,17628.57
+2014-01-01,19905.05
+2014-04-01,19370.01
+2014-07-01,22609.42
+2014-10-01,20847.64
+2015-01-01,25160.03
+2015-04-01,26376.12
+2015-07-01,30709.11
+2015-10-01,28427.74
+2016-01-01,31770.19
+2016-04-01,33540.70
+2016-07-01,35564.10
+2016-10-01,36377.03
+2017-01-01,41252.10
+2017-04-01,47138.21
+2017-07-01,56096.90
+2017-10-01,52838.28
+2018-01-01,56672.95
+2018-04-01,63083.56
+2018-07-01,76672.68
+2018-10-01,75088.54
+2019-01-01,78769.81
+2019-04-01,87255.83
+2019-07-01,99103.90
+2019-10-01,103265.11
+2020-01-01,101339.37
+2020-04-01,111949.08
+2020-07-01,148634.52
+,
+,
+,
+,
+,
+,

fortensor.csv

@@ -0,0 +1,40 @@
+observation_date,ECOMSA
+2011,45104.57
+2012,60265.08
+2013,69114.95
+2014,82732.12
+2015,110673
+2016,137252
+2017,197325.5
+2018,271517.7
+2019,368394.7
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,
+,

lineerreg.py

@@ -0,0 +1,16 @@
+import numpy as np
+import pandas as pd
+import matplotlib.pyplot as plt
+
+dataset = pd.read_csv('fortensor.csv')
+X = dataset.iloc[:,:-1].values  #independent variable array
+y = dataset.iloc[:,1].values  #dependent variable vector
+
+from sklearn.model_selection import train_test_split
+X_train, X_test, y_train, y_test = train_test_split(X,y,test_size=1/3,random_state=0)
+
+from sklearn.linear_model import LinearRegression
+regressor = LinearRegression()
+regressor.fit(X_train,y_train) #actually produces the linear eqn for the data
+y_pred = regressor.predict(X_test)
+print("y is \n",y_pred)

newtest.py

@@ -0,0 +1,43 @@
+import pandas as pd
+
+# create dataset
+df = pd.DataFrame({'dates': [2011,2012,2013,2014,2015,2016,2017,2018,2019],
+                   'score': [45104.57, 60265.08, 69114.95, 82732.12, 110673, 137252, 197325.5, 271517.7, 368394.7]})
+
+import matplotlib.pyplot as plt
+
+plt.scatter(df.dates, df.score)
+plt.title('Hours studied vs. Exam Score')
+plt.xlabel('Hours')
+plt.ylabel('Score')
+plt.show()
+
+df.boxplot(column=['score'])
+import statsmodels.api as sm
+
+#define response variable
+y = df['score']
+
+#define explanatory variable
+x = df[['dates']]
+
+#add constant to predictor variables
+x = sm.add_constant(x)
+
+#fit linear regression model
+model = sm.OLS(y, x).fit()
+
+#view model summary
+print(model.summary())
+#define figure size
+fig = plt.figure(figsize=(12,8))
+
+#produce residual plots
+fig = sm.graphics.plot_regress_exog(model, 'dates', fig=fig)
+
+#define residuals
+res = model.resid
+
+#create Q-Q plot
+fig = sm.qqplot(res, fit=True, line="45")
+plt.show()

tensortest.py

@@ -0,0 +1,15 @@
+import tensorflow as tf
+import pandas as pd
+from tensorflow import keras
+import numpy as np
+
+def house_model(y_new):
+    xs = np.array([20.11,20.12,20.13,20.14,20.15,20.16,20.17,20.18,20.19])
+    ys = np.array([100.0,150.0,200.0,250.0,300.0,350.0,400.0,450.0,500.0])
+    model = tf.keras.Sequential([keras.layers.Dense(units = 2,input_shape=[1])])
+    model.compile(optimizer='sgd',loss='mean_squared_error')
+    model.fit(xs,ys,epochs=200)
+    return model.predict(y_new)[0]
+
+test = house_model([30.12])
+print(test)