PractiquesPart3

import pandas as pd

df = pd.read_csv("ArcTecSw_2021_BigData_Practica_Part3_amoni.csv", index_col=0)

df.shape

df.head()

df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 147 entries, 0 to 214
Data columns (total 8 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   target  147 non-null    float64
 1   1       145 non-null    float64
 2   2       145 non-null    float64
 3   3       32 non-null     float64
 4   4       31 non-null     float64
 5   5       33 non-null     float64
 6   6       37 non-null     float64
 7   7       37 non-null     float64
dtypes: float64(8)
memory usage: 10.3 KB

df.describe()

df.corr()

import matplotlib.pyplot as plt

f, ax = plt.subplots(nrows=3,ncols=3) f.set_figheight(12) f.set_figwidth(15) ax[0,0].scatter(df['target'],df['1']) ax[0,1].scatter(df['target'],df['2']) ax[0,2].scatter(df['target'],df['3']) ax[1,0].scatter(df['target'],df['4']) ax[1,1].scatter(df['target'],df['5']) ax[1,2].scatter(df['target'],df['6']) ax[2,0].scatter(df['target'],df['7']) ax[2,1].remove() ax[2,2].remove()

processed_df = df.drop(['3','4','5','6','7'], axis=1)

processed_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 147 entries, 0 to 214
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   target  147 non-null    float64
 1   1       145 non-null    float64
 2   2       145 non-null    float64
dtypes: float64(3)
memory usage: 4.6 KB

processed_df = processed_df.dropna()

processed_df.info()

<class 'pandas.core.frame.DataFrame'>
Int64Index: 144 entries, 0 to 214
Data columns (total 3 columns):
 #   Column  Non-Null Count  Dtype  
---  ------  --------------  -----  
 0   target  144 non-null    float64
 1   1       144 non-null    float64
 2   2       144 non-null    float64
dtypes: float64(3)
memory usage: 4.5 KB

processed_df.head()

station_1 = processed_df['1']

station_2 = processed_df['2']

mean = (station_1+station_2)/2

relation = processed_df['target']/mean

processed_df['relation'] = relation

processed_df['mean'] = processed_df['1']/processed_df['2']

processed_df.head()

from sklearn.model_selection import train_test_split

x_train, x_test, y_train, y_test = train_test_split(processed_df[["1","2","relation","mean"]], processed_df[["target"]], test_size=0.10, random_state=42)

from sklearn.linear_model import SGDRegressor

reg_sgdr = SGDRegressor()

reg_sgdr.fit(x_train, y_train)

/shared-libs/python3.8/py/lib/python3.8/site-packages/sklearn/utils/validation.py:63: DataConversionWarning: A column-vector y was passed when a 1d array was expected. Please change the shape of y to (n_samples, ), for example using ravel().
  return f(*args, **kwargs)

from sklearn.metrics import mean_absolute_error, mean_squared_error, r2_score

mean_absolute_error(y_test, reg_sgdr.predict(x_test))

mean_squared_error(y_test, reg_sgdr.predict(x_test))