diff --git a/docs/class_diagram.drawio b/docs/class_diagram.drawio
new file mode 100644
index 0000000000000000000000000000000000000000..51066a5cef382326c8c3e1c8477dd81a52567f4d
--- /dev/null
+++ b/docs/class_diagram.drawio
@@ -0,0 +1 @@
+<mxfile host="Electron" modified="2023-07-12T16:27:44.192Z" agent="5.0 (Macintosh; Intel Mac OS X 10_15_7) AppleWebKit/537.36 (KHTML, like Gecko) draw.io/15.8.7 Chrome/91.0.4472.164 Electron/13.6.2 Safari/537.36" etag="cKdbLBWRQm2rR1pnQ_-2" version="15.8.7" type="device"><diagram id="C5RBs43oDa-KdzZeNtuy" name="Page-1">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</diagram></mxfile>
\ No newline at end of file
diff --git a/docs/class_diagram.png b/docs/class_diagram.png
new file mode 100644
index 0000000000000000000000000000000000000000..47fb58150dfebd880bcfdd8a60dfc09ad90c8635
Binary files /dev/null and b/docs/class_diagram.png differ
diff --git a/src/Dataset.py b/src/Dataset.py
index 72cb721bc4450a5a21a3a99f195ec3819c670188..fc3c33476a6967cb44c571c2fb2433efff939ecc 100644
--- a/src/Dataset.py
+++ b/src/Dataset.py
@@ -1,5 +1,6 @@
import numpy as np
import pandas as pd
+import logging
class Dataset:
@@ -11,8 +12,23 @@ class Dataset:
dataset_filename (str): the path of the dataset,
relative to the location of the file calling this function.
"""
- raw_dataframe = pd.read_csv(dataset_filename, encoding="windows-1254")
+ if type(dataset_filename) != str:
+ logging.error("parameter `dataset_filename` is not a string")
+ raise ValueError(f"{dataset_filename} is not a string")
+
+ if not dataset_filename.endswith(".csv"):
+ logging.error("dataset filename should be CSV")
+ raise OSError(f"{dataset_filename} is not a CSV file.")
+ try:
+ raw_dataframe = pd.read_csv(
+ dataset_filename, encoding="windows-1254"
+ )
+ logging.info("Dataframe successfully loaded")
+ except FileNotFoundError as e:
+ logging.error("CSV file not found")
+ raise e
self.dataframe = self.preprocess_dataset(raw_dataframe)
+ logging.info("Dataset class successfully initialised")
def preprocess_dataset(self, raw_dataframe: pd.DataFrame) -> pd.DataFrame:
"""preprocess dataframe immediately after loading it.
@@ -25,6 +41,12 @@ class Dataset:
Returns:
pd.DataFrame: resulting preprocessed dataframe.
"""
+ if type(raw_dataframe) != pd.DataFrame:
+ logging.error(
+ "parameter `raw_dataframe` is not a pandas DataFrame"
+ )
+ raise ValueError(f"{raw_dataframe} is not a pandas DataFrame")
+
dataframe = self._drop_unnecessary_columns(
raw_dataframe
) # for conveneince
@@ -39,6 +61,10 @@ class Dataset:
return dataframe
def get_is_competitive_col(self, dataframe: pd.DataFrame):
+ if type(dataframe) != pd.DataFrame:
+ logging.error("parameter `dataframe` is not a pandas DataFrame")
+ raise ValueError(f"{dataframe} is not a pandas DataFrame")
+
is_competitive_col = np.zeros(shape=len(dataframe))
is_competitive_col[
(dataframe["whyplay"] == "improving")
@@ -64,6 +90,10 @@ class Dataset:
Returns:
pd.DataFrame: the dataframe.
"""
+
+ if type(dataframe) != pd.DataFrame:
+ logging.error("parameter `dataframe` is not a pandas DataFrame")
+ raise ValueError(f"{dataframe} is not a pandas DataFrame")
rows_to_drop = (
[
"League",
@@ -92,6 +122,10 @@ class Dataset:
Returns:
pd.DataFrame: the dataframe.
"""
+ if type(dataframe) != pd.DataFrame:
+ logging.error("parameter `dataframe` is not a pandas DataFrame")
+ raise ValueError(f"{dataframe} is not a pandas DataFrame")
+
# drop rows where users did not accept to having their data used
dataframe = dataframe.drop(
dataframe[dataframe["accept"] != "Accept"].index,
@@ -108,6 +142,10 @@ class Dataset:
Returns:
pd.Series: the Is_competitive column.
"""
+ if type(dataframe) != pd.DataFrame:
+ logging.error("parameter `dataframe` is not a pandas DataFrame")
+ raise ValueError(f"{dataframe} is not a pandas DataFrame")
+
dataframe["whyplay"] = dataframe["whyplay"].str.lower()
most_common_whyplay_reasons = list(
dataframe.groupby("whyplay")
@@ -122,7 +160,7 @@ class Dataset:
is_competitive_col = self.get_is_competitive_col(dataframe)
return is_competitive_col
- def treat_outliers(self, df, colname):
+ def treat_outliers(self, df, colname) -> pd.DataFrame:
q = df[colname].quantile(0.99)
return df[df[colname] < q]
@@ -138,6 +176,10 @@ class Dataset:
Returns:
pd.Series: the anxiety score column.
"""
+ if type(dataframe) != pd.DataFrame:
+ logging.error("parameter `dataframe` is not a pandas DataFrame")
+ raise ValueError(f"{dataframe} is not a pandas DataFrame")
+
gad_max = 21
gad_min = 0
gad_normalised = (dataframe["GAD_T"] - gad_min) / gad_max
@@ -161,6 +203,10 @@ class Dataset:
Returns:
pd.Series: the boolean narcissist column.
"""
+ if type(dataframe) != pd.DataFrame:
+ logging.error("parameter `dataframe` is not a pandas DataFrame")
+ raise ValueError(f"{dataframe} is not a pandas DataFrame")
+
return np.where(dataframe["Narcissism"] <= 1.0, True, False)
def get_dataframe(self) -> pd.DataFrame:
@@ -183,6 +229,13 @@ class Dataset:
Returns:
pd.Series: The sorted column.
"""
+ if type(colname) != str:
+ logging.error("parameter `colname` is not a string")
+ raise ValueError(f"{colname} is not a string")
+ if type(colname) not in (None, bool):
+ logging.error("parameter `ascending` is not a bool or None")
+ raise ValueError(f"{colname} is not a bool or None")
+
return self.dataframe[colname].sort_values(ascending=ascending)
def get_unique_column_values(self, colname: str):
@@ -195,6 +248,10 @@ class Dataset:
string array: an array of strings containing the unique values
present in the column
"""
+ if type(colname) != str:
+ logging.error("parameter `colname` is not a string")
+ raise ValueError(f"{colname} is not a string")
+
return self.dataframe[colname].explode().unique()
def get_category_counts(
@@ -210,6 +267,13 @@ class Dataset:
Returns:
pd.Series: the counted categories.
"""
+ if type(colname) != str:
+ logging.error("parameter `colname` is not a string")
+ raise ValueError(f"{colname} is not a string")
+ if type(colname) not in (None, bool):
+ logging.error("parameter `ascending` is not a bool or None")
+ raise ValueError(f"{colname} is not a bool or None")
+
grouped_size = self.dataframe.groupby(colname).size()
return (
grouped_size
diff --git a/src/Plotter.py b/src/Plotter.py
index c9055befddaf2a526378850a681c37e187803df6..c8d9051a3b7e2319a463cf91aba90b003908e7a9 100644
--- a/src/Plotter.py
+++ b/src/Plotter.py
@@ -3,18 +3,61 @@ import matplotlib.pyplot as plt
import pandas as pd
import seaborn as sns
from .Dataset import Dataset
-
+import logging
class Plotter:
def __init__(self, dataset: Dataset):
+ if type(dataset) != Dataset:
+ logging.error("dataset parameter is not of type Dataset")
+ raise ValueError(f"{dataset} is not of type Dataset")
+
self.ds = dataset
self.df = dataset.get_dataframe()
- def customize_plot(self, fig, ax, styling_params):
+ def customize_plot(self, fig, ax, styling_params) -> None:
+ """ customize_plot
+
+ Args:
+ fig (plt.figure.Figure),
+ ax (plt.axes.Axes),
+ styling_params (dict)
+
+
+ Returns:
+ None
+ """
if styling_params.get("title"):
ax.set_title(styling_params["title"])
- def distribution_plot(self, target):
+ def distribution_plot(self, target, styling_params = {}) -> None:
+ """ plot a distribution plot.
+
+ Args:
+ target (str, must be present as a column in the dataset),
+ styling_params (dict)
+
+
+ Returns:
+ None
+ """
+
+ # implementing sensible logging and error catching
+ if (type(target) != str):
+ logging.error("parameter target should be a string.")
+ raise ValueError("parameter target should be a string.")
+
+ if not (target in self.df.columns):
+ logging.error("parameter target cannot be found in the dataset.")
+ raise ValueError(
+ "parameter target cannot be found in the dataset."
+ )
+
+ if (type(styling_params) != dict):
+ logging.error("parameter styling params should be a dict.")
+ raise ValueError("parameter styling params should be a dict.")
+
+ # plotting the plot
+
grouped_data = self.df.groupby(target).size()
plt.barh(grouped_data.index, grouped_data.values)
print(
@@ -28,7 +71,44 @@ class Plotter:
def plot_categorical_bar_chart(
self, category1, category2, styling_params={}
- ):
+ ) -> None:
+ """ plot a categorical bar chart.
+
+ Args:
+ category1 (str, must be present as a column in the dataset),
+ category2 (str, must be present as a column in the dataset),
+ styling_params (dict)
+
+
+ Returns:
+ None
+ """
+ # implementing sensible logging and error catching
+ if (type(category1) != str):
+ logging.error("parameter category1 should be a string.")
+ raise ValueError("parameter category1 should be a string.")
+
+ if not (category1 in self.df.columns):
+ logging.error("parameter category1 cannot be found in the dataset.")
+ raise ValueError(
+ "parameter category1 cannot be found in the dataset."
+ )
+
+ if (type(category2) != str):
+ logging.error("parameter category2 should be a string.")
+ raise ValueError("parameter category2 should be a string.")
+
+ if not (category2 in self.df.columns):
+ logging.error("parameter category2 cannot be found in the dataset.")
+ raise ValueError(
+ "parameter category2 cannot be found in the dataset."
+ )
+
+ if (type(styling_params) != dict):
+ logging.error("parameter styling params should be a dict.")
+ raise ValueError("parameter styling params should be a dict.")
+
+ # plotting the plot
ct = pd.crosstab(self.df[category1], self.df[category2])
# Calculate percentages by row
ct_percent = ct.apply(lambda r: r / r.sum() * 100, axis=0)
@@ -36,14 +116,91 @@ class Plotter:
self.customize_plot(fig, ax, styling_params)
ct_percent.plot(kind="bar", ax=ax)
- def plot_categorical_boxplot(self, target, category, styling_params={}):
+ def plot_categorical_boxplot(
+ self, target, category, styling_params={}
+ ) -> None:
+ """ plot a categorical boxplot.
+
+ Args:
+ target (str, must be present as a column in the dataset),
+ category (str, must be present as a column in the dataset),
+ styling_params (dict)
+
+
+ Returns:
+ None
+ """
+ # implementing sensible logging and error catching
+ if (type(target) != str):
+ logging.error("parameter target should be a string.")
+ raise ValueError("parameter target should be a string.")
+
+ if not (target in self.df.columns):
+ logging.error("parameter target cannot be found in the dataset.")
+ raise ValueError(
+ "parameter target cannot be found in the dataset."
+ )
+
+ if (type(category) != str):
+ logging.error("parameter category should be a string.")
+ raise ValueError("parameter category should be a string.")
+
+ if not (category in self.df.columns):
+ logging.error("parameter category cannot be found in the dataset.")
+ raise ValueError(
+ "parameter category cannot be found in the dataset."
+ )
+
+ if (type(styling_params) != dict):
+ logging.error("parameter styling params should be a dict.")
+ raise ValueError("parameter styling params should be a dict.")
+
+ # plotting the plot
fig, ax = plt.subplots()
self.customize_plot(fig, ax, styling_params)
sns.boxplot(x=category, y=target, data=self.df, palette="rainbow")
def plot_categorical_histplot(
self, target, category, styling_params={}, bins=30
- ):
+ ) -> None:
+ """ plot a categorical hisplot.
+
+ Args:
+ target (str, must be present as a column in the dataset),
+ category (str, must be present as a column in the dataset),
+ styling_params (dict)
+
+
+ Returns:
+ None
+ """
+ # implementing sensible logging and error catching
+ if (type(target) != str):
+ logging.error("parameter target should be a string.")
+ raise ValueError("parameter target should be a string.")
+
+ if not (target in self.df.columns):
+ logging.error("parameter target cannot be found in the dataset.")
+ raise ValueError(
+ "parameter target cannot be found in the dataset."
+ )
+
+ if (type(category) != str):
+ logging.error("parameter category should be a string.")
+ raise ValueError("parameter category should be a string.")
+
+ if not (category in self.df.columns):
+ logging.error("parameter category cannot be found in the dataset.")
+ raise ValueError(
+ "parameter category cannot be found in the dataset."
+ )
+
+ if (type(styling_params) != dict):
+ logging.error("parameter styling params should be a dict.")
+ raise ValueError("parameter styling params should be a dict.")
+
+ # plotting the plot
+
uniques = self.ds.get_unique_column_values(category)
fig, ax = plt.subplots()
self.customize_plot(fig, ax, styling_params)
@@ -57,7 +214,45 @@ class Plotter:
alpha=0.5,
)
- def plot_scatterplot(self, target1, target2, styling_params={}):
+ def plot_scatterplot(self, target1, target2, styling_params={}) -> None:
+ """ plot a scatterplot.
+
+ Args:
+ target1 (str, must be present as a column in the dataset),
+ target2 (str, must be present as a column in the dataset),
+ styling_params (dict)
+
+
+ Returns:
+ None
+ """
+
+ # implementing sensible logging and error catching
+ if (type(target1) != str):
+ logging.error("parameter target1 should be a string.")
+ raise ValueError("parameter target1 should be a string.")
+
+ if not (target1 in self.df.columns):
+ logging.error("parameter target1 cannot be found in the dataset.")
+ raise ValueError(
+ "parameter target1 cannot be found in the dataset."
+ )
+
+ if (type(target2) != str):
+ logging.error("parameter target2 should be a string.")
+ raise ValueError("parameter target2 should be a string.")
+
+ if not (target2 in self.df.columns):
+ logging.error("parameter target2 cannot be found in the dataset.")
+ raise ValueError(
+ "parameter target2 cannot be found in the dataset."
+ )
+
+ if (type(styling_params) != dict):
+ logging.error("parameter styling params should be a dict.")
+ raise ValueError("parameter styling params should be a dict.")
+
+ # plotting the plot
fig, ax = plt.subplots()
self.customize_plot(fig, ax, styling_params)
- ax.scatter(self.df[target1], self.df[target2])
+ ax.scatter(self.df[target1], self.df[target2])
\ No newline at end of file