Update case study notebooks + regenerate

jorisvandenbossche · jorisvandenbossche · commit 3c995421282c · 2021-05-30T11:47:02.000+02:00
diff --git a/_solved/case1_bike_count.ipynb b/_solved/case1_bike_count.ipynb
diff --git a/_solved/case2_observations_analysis.ipynb b/_solved/case2_observations_analysis.ipynb
diff --git a/_solved/case2_observations_processing.ipynb b/_solved/case2_observations_processing.ipynb
diff --git a/_solved/case3_bacterial_resistance_lab_experiment.ipynb b/_solved/case3_bacterial_resistance_lab_experiment.ipynb
diff --git a/notebooks/_solutions/case1_bike_count10.py b/notebooks/_solutions/case1_bike_count10.py
@@ -1,23 +1,23 @@
 def process_bike_count_data(df):
     """Process the provided dataframe: parse datetimes and rename columns.
-    
+
     Parameters
     ----------
     df : pandas.DataFrame
-        DataFrame as read from the raw `fietstellingen`, 
-        containing the `datum`, `tijd`, `ri Centrum` 
+        DataFrame as read from the raw `fietstellingen`,
+        containing the `datum`, `tijd`, `ri Centrum`
         and `ri Mariakerke` columns.
-        
+
     Returns
     -------
     df2 : pandas.DataFrame
-        DataFrame with the datetime info as index and the 
-        `direction_centre` and `direction_mariakerke` columns 
+        DataFrame with the datetime info as index and the
+        `direction_centre` and `direction_mariakerke` columns
         with the counts.
     """
-    df.index = pd.to_datetime(df['datum'] + ' ' + df['tijd'], 
+    df.index = pd.to_datetime(df['datum'] + ' ' + df['tijd'],
                               format="%d/%m/%Y %H:%M")
     df2 = df.drop(columns=['datum', 'tijd'])
-    df2 = df2.rename(columns={'ri Centrum': 'direction_centre', 
+    df2 = df2.rename(columns={'ri Centrum': 'direction_centre',
                               'ri Mariakerke':'direction_mariakerke'})
     return df2
diff --git a/notebooks/_solutions/case1_bike_count9.py b/notebooks/_solutions/case1_bike_count9.py
@@ -1,2 +1,2 @@
-df2 = df2.rename(columns={'ri Centrum': 'direction_centre', 
+df2 = df2.rename(columns={'ri Centrum': 'direction_centre',
                           'ri Mariakerke':'direction_mariakerke'})
diff --git a/notebooks/_solutions/case2_observations_analysis1.py b/notebooks/_solutions/case2_observations_analysis1.py
@@ -1,2 +1,2 @@
-survey_data_processed = pd.read_csv("data/survey_data_completed.csv", 
+survey_data_processed = pd.read_csv("data/survey_data_completed.csv",
                                     parse_dates=['eventDate'], index_col="occurrenceID")
diff --git a/notebooks/_solutions/case2_observations_analysis10.py b/notebooks/_solutions/case2_observations_analysis10.py
@@ -1,2 +1,2 @@
-survey_data = survey_data_unique.dropna(subset=['species']).copy()
-survey_data['name'] = survey_data['genus'] + ' ' + survey_data['species']
+mask = survey_data_unique['species'].isna() & survey_data_unique['sex'].notna()
+not_identified = survey_data_unique[mask]
diff --git a/notebooks/_solutions/case2_observations_analysis11.py b/notebooks/_solutions/case2_observations_analysis11.py
@@ -1 +1 @@
-survey_data.groupby("name").size().nlargest(8)
+non_rodent_species = survey_data[survey_data['taxa'].isin(['Rabbit', 'Bird', 'Reptile'])]
diff --git a/notebooks/_solutions/case2_observations_analysis12.py b/notebooks/_solutions/case2_observations_analysis12.py
@@ -1 +1 @@
-survey_data['name'].value_counts()[:8]
+r_species = survey_data[survey_data['name'].str.lower().str.startswith('r')]
diff --git a/notebooks/_solutions/case2_observations_analysis13.py b/notebooks/_solutions/case2_observations_analysis13.py
@@ -1,11 +1 @@
-n_species_per_plot = survey_data.groupby(["verbatimLocality"])["name"].nunique()
-
-fig, ax = plt.subplots(figsize=(6, 6))
-n_species_per_plot.plot(kind="barh", ax=ax, color="lightblue")
-ax.set_ylabel("plot number")
-
-# Alternative option:
-# inspired on the pivot table we already had:
-# species_per_plot = survey_data.reset_index().pivot_table(
-#     index="name", columns="verbatimLocality", values="occurrenceID", aggfunc='count')
-# n_species_per_plot = species_per_plot.count()
+non_bird_species = survey_data[survey_data['taxa'] != 'Bird']
diff --git a/notebooks/_solutions/case2_observations_analysis14.py b/notebooks/_solutions/case2_observations_analysis14.py
@@ -1,6 +1,4 @@
-n_plots_per_species = survey_data.groupby(["name"])["verbatimLocality"].nunique().sort_values()
-
-fig, ax = plt.subplots(figsize=(8, 8))
-n_plots_per_species.plot(kind="barh", ax=ax, color='0.4')
-ax.set_xlabel("Number of plots");
-ax.set_ylabel("");
+birds_85_89 = survey_data[(survey_data["eventDate"] >= "1985-01-01")
+                          & (survey_data["eventDate"] <= "1989-12-31 23:59")
+                          & (survey_data['taxa'] == 'Bird')]
+birds_85_89.head()
diff --git a/notebooks/_solutions/case2_observations_analysis15.py b/notebooks/_solutions/case2_observations_analysis15.py
@@ -1,2 +1,5 @@
-n_plot_sex = survey_data.groupby(["sex", "verbatimLocality"]).size().rename("count").reset_index()
-n_plot_sex.head()
+# alternative solution
+birds_85_89 = survey_data[(survey_data["eventDate"].dt.year >= 1985)
+                          & (survey_data["eventDate"].dt.year <= 1989)
+                          & (survey_data['taxa'] == 'Bird')]
+birds_85_89.head()
diff --git a/notebooks/_solutions/case2_observations_analysis16.py b/notebooks/_solutions/case2_observations_analysis16.py
@@ -1,2 +1,4 @@
-pivoted = n_plot_sex.pivot_table(columns="sex", index="verbatimLocality", values="count")
-pivoted.head()
+# Multiple lines
+obs_with_weight = survey_data.dropna(subset=["wgt"])
+median_weight = obs_with_weight.groupby(['name'])["wgt"].median()
+median_weight.sort_values(ascending=False)
diff --git a/notebooks/_solutions/case2_observations_analysis17.py b/notebooks/_solutions/case2_observations_analysis17.py
@@ -1,2 +1,7 @@
-sns.catplot(data=survey_data, x="verbatimLocality", 
-            hue="sex", kind="count", height=3, aspect=3)
+# Single line statement
+(survey_data
+     .dropna(subset=["wgt"])
+     .groupby(['name'])["wgt"]
+     .median()
+     .sort_values(ascending=False)
+)
diff --git a/notebooks/_solutions/case2_observations_analysis18.py b/notebooks/_solutions/case2_observations_analysis18.py
@@ -1,8 +1 @@
-species_per_plot = survey_data.reset_index().pivot_table(index="name", 
-                                                         columns="verbatimLocality", 
-                                                         values="occurrenceID", 
-                                                         aggfunc='count')
-
-# alternative ways to calculate this
-#species_per_plot = survey_data.groupby(['name', 'plot_id']).size().unstack(level=-1)
-#species_per_plot = pd.crosstab(survey_data['name'], survey_data['plot_id'])
+survey_data.groupby("name").size().nlargest(8)
diff --git a/notebooks/_solutions/case2_observations_analysis19.py b/notebooks/_solutions/case2_observations_analysis19.py
@@ -1,2 +1 @@
-fig, ax = plt.subplots(figsize=(8,8))
-sns.heatmap(species_per_plot, ax=ax, cmap='Greens')
+survey_data['name'].value_counts()[:8]
diff --git a/notebooks/_solutions/case2_observations_analysis20.py b/notebooks/_solutions/case2_observations_analysis20.py
@@ -1 +1,11 @@
-survey_data.resample('A', on='eventDate').size().plot()
+n_species_per_plot = survey_data.groupby(["verbatimLocality"])["name"].nunique()
+
+fig, ax = plt.subplots(figsize=(6, 6))
+n_species_per_plot.plot(kind="barh", ax=ax, color="lightblue")
+ax.set_ylabel("plot number")
+
+# Alternative option:
+# inspired on the pivot table we already had:
+# species_per_plot = survey_data.reset_index().pivot_table(
+#     index="name", columns="verbatimLocality", values="occurrenceID", aggfunc='count')
+# n_species_per_plot = species_per_plot.count()
diff --git a/notebooks/_solutions/case2_observations_analysis21.py b/notebooks/_solutions/case2_observations_analysis21.py
@@ -1,5 +1,6 @@
-heatmap_prep = survey_data.pivot_table(index=survey_data['eventDate'].dt.year, 
-                                       columns=survey_data['eventDate'].dt.month, 
-                                       values='species', aggfunc='count')
-fig, ax = plt.subplots(figsize=(10, 8))
-ax = sns.heatmap(heatmap_prep, cmap='Reds')
+n_plots_per_species = survey_data.groupby(["name"])["verbatimLocality"].nunique().sort_values()
+
+fig, ax = plt.subplots(figsize=(8, 8))
+n_plots_per_species.plot(kind="barh", ax=ax, color='0.4')
+ax.set_xlabel("Number of plots");
+ax.set_ylabel("");
diff --git a/notebooks/_solutions/case2_observations_analysis22.py b/notebooks/_solutions/case2_observations_analysis22.py
@@ -1 +1,2 @@
-merriami = survey_data[survey_data["name"] == "Dipodomys merriami"]
+n_plot_sex = survey_data.groupby(["sex", "verbatimLocality"]).size().rename("count").reset_index()
+n_plot_sex.head()
diff --git a/notebooks/_solutions/case2_observations_analysis23.py b/notebooks/_solutions/case2_observations_analysis23.py
@@ -1,4 +1,2 @@
-fig, ax = plt.subplots()
-merriami.groupby(merriami['eventDate'].dt.month).size().plot(kind="barh", ax=ax)
-ax.set_xlabel("number of occurrences");
-ax.set_ylabel("Month of the year");
+pivoted = n_plot_sex.pivot(columns="sex", index="verbatimLocality", values="count")
+pivoted.head()
diff --git a/notebooks/_solutions/case2_observations_analysis24.py b/notebooks/_solutions/case2_observations_analysis24.py
@@ -1,2 +1,2 @@
-subsetspecies = survey_data[survey_data["name"].isin(['Dipodomys merriami', 'Dipodomys ordii',
-                                                      'Reithrodontomys megalotis', 'Chaetodipus baileyi'])]
+sns.catplot(data=n_plot_sex, x="verbatimLocality", y="count",
+            hue="sex", kind="bar", height=3, aspect=3)
diff --git a/notebooks/_solutions/case2_observations_analysis25.py b/notebooks/_solutions/case2_observations_analysis25.py
@@ -1 +1,2 @@
-month_evolution = subsetspecies.groupby("name").resample('M', on='eventDate').size()
+sns.catplot(data=survey_data, x="verbatimLocality",
+            hue="sex", kind="count", height=3, aspect=3)
diff --git a/notebooks/_solutions/case2_observations_analysis26.py b/notebooks/_solutions/case2_observations_analysis26.py
@@ -1,2 +1,8 @@
-species_evolution = month_evolution.unstack(level=0)
-axs = species_evolution.plot(subplots=True, figsize=(14, 8), sharey=True)
+species_per_plot = survey_data.pivot_table(index="name",
+                                           columns="verbatimLocality",
+                                           values="datasetName",
+                                           aggfunc='count')
+
+# alternative ways to calculate this
+#species_per_plot = survey_data.groupby(['name', 'verbatimLocality']).size().unstack(level=-1)
+#pecies_per_plot = pd.crosstab(survey_data['name'], survey_data['verbatimLocality'])
diff --git a/notebooks/_solutions/case2_observations_analysis27.py b/notebooks/_solutions/case2_observations_analysis27.py
@@ -1,5 +1,2 @@
-# Given as solution..
-subsetspecies = survey_data[survey_data["name"].isin(['Dipodomys merriami', 'Dipodomys ordii',
-                                                      'Reithrodontomys megalotis', 'Chaetodipus baileyi'])]
-month_evolution = subsetspecies.groupby("name").resample('M', on='eventDate').size().rename("counts")
-month_evolution = month_evolution.reset_index()
+fig, ax = plt.subplots(figsize=(8,8))
+sns.heatmap(species_per_plot, ax=ax, cmap='Greens')
diff --git a/notebooks/_solutions/case2_observations_analysis28.py b/notebooks/_solutions/case2_observations_analysis28.py
@@ -1,2 +1 @@
-sns.relplot(data=month_evolution, x='eventDate', y="counts", 
-            row="name", kind="line", hue="name", height=2, aspect=5)
+survey_data.resample('A', on='eventDate').size().plot()
diff --git a/notebooks/_solutions/case2_observations_analysis29.py b/notebooks/_solutions/case2_observations_analysis29.py
@@ -1,4 +1,5 @@
-fig, ax = plt.subplots()
-survey_data.groupby(survey_data["eventDate"].dt.dayofweek).size().plot(kind='barh', color='#66b266', ax=ax)
-import calendar
-xticks = ax.set_yticklabels(calendar.day_name)
+heatmap_prep = survey_data.pivot_table(index=survey_data['eventDate'].dt.year,
+                                       columns=survey_data['eventDate'].dt.month,
+                                       values='species', aggfunc='count')
+fig, ax = plt.subplots(figsize=(10, 8))
+ax = sns.heatmap(heatmap_prep, cmap='Reds')
diff --git a/notebooks/_solutions/case2_observations_analysis30.py b/notebooks/_solutions/case2_observations_analysis30.py
@@ -0,0 +1 @@
+merriami = survey_data[survey_data["name"] == "Dipodomys merriami"]
diff --git a/notebooks/_solutions/case2_observations_analysis31.py b/notebooks/_solutions/case2_observations_analysis31.py
@@ -0,0 +1,4 @@
+fig, ax = plt.subplots()
+merriami.groupby(merriami['eventDate'].dt.month).size().plot(kind="barh", ax=ax)
+ax.set_xlabel("number of occurrences");
+ax.set_ylabel("Month of the year");
diff --git a/notebooks/_solutions/case2_observations_analysis32.py b/notebooks/_solutions/case2_observations_analysis32.py
@@ -0,0 +1,2 @@
+subsetspecies = survey_data[survey_data["name"].isin(['Dipodomys merriami', 'Dipodomys ordii',
+                                                      'Reithrodontomys megalotis', 'Chaetodipus baileyi'])]
diff --git a/notebooks/_solutions/case2_observations_analysis33.py b/notebooks/_solutions/case2_observations_analysis33.py
@@ -0,0 +1 @@
+month_evolution = subsetspecies.groupby("name").resample('M', on='eventDate').size()
diff --git a/notebooks/_solutions/case2_observations_analysis34.py b/notebooks/_solutions/case2_observations_analysis34.py
@@ -0,0 +1,2 @@
+species_evolution = month_evolution.unstack(level=0)
+axs = species_evolution.plot(subplots=True, figsize=(14, 8), sharey=True)
diff --git a/notebooks/_solutions/case2_observations_analysis35.py b/notebooks/_solutions/case2_observations_analysis35.py
@@ -0,0 +1,6 @@
+# Given as solution..
+subsetspecies = survey_data[survey_data["name"].isin(['Dipodomys merriami', 'Dipodomys ordii',
+                                                      'Reithrodontomys megalotis', 'Chaetodipus baileyi'])]
+month_evolution = subsetspecies.groupby("name").resample('M', on='eventDate').size().rename("counts")
+month_evolution = month_evolution.reset_index()
+month_evolution.head()
diff --git a/notebooks/_solutions/case2_observations_analysis36.py b/notebooks/_solutions/case2_observations_analysis36.py
@@ -0,0 +1,2 @@
+sns.relplot(data=month_evolution, x='eventDate', y="counts",
+            row="name", kind="line", hue="name", height=2, aspect=5)
diff --git a/notebooks/_solutions/case2_observations_analysis37.py b/notebooks/_solutions/case2_observations_analysis37.py
@@ -0,0 +1,3 @@
+year_evolution = survey_data.groupby("taxa").resample('A', on='eventDate').size()
+year_evolution.name = "counts"
+year_evolution = year_evolution.reset_index()
diff --git a/notebooks/_solutions/case2_observations_analysis38.py b/notebooks/_solutions/case2_observations_analysis38.py
@@ -0,0 +1,3 @@
+sns.relplot(data=year_evolution, x='eventDate', y="counts",
+            col="taxa", col_wrap=2, kind="line", height=2, aspect=5,
+            facet_kws={"sharey": False})
diff --git a/notebooks/_solutions/case2_observations_analysis39.py b/notebooks/_solutions/case2_observations_analysis39.py
@@ -0,0 +1,4 @@
+fig, ax = plt.subplots()
+survey_data.groupby(survey_data["eventDate"].dt.dayofweek).size().plot(kind='barh', color='#66b266', ax=ax)
+import calendar
+xticks = ax.set_yticklabels(calendar.day_name)
diff --git a/notebooks/_solutions/case2_observations_analysis8.py b/notebooks/_solutions/case2_observations_analysis8.py
@@ -1 +1 @@
-len(survey_data_unique.dropna()), len(survey_data_unique.dropna(subset=['species']))
+len(survey_data_unique)
diff --git a/notebooks/_solutions/case2_observations_analysis9.py b/notebooks/_solutions/case2_observations_analysis9.py
@@ -1,2 +1 @@
-mask = survey_data_unique['species'].isna() & survey_data_unique['sex'].notna()
-not_identified = survey_data_unique[mask]
+len(survey_data_unique.dropna()), len(survey_data_unique.dropna(subset=['species']))
diff --git a/notebooks/_solutions/case2_observations_processing10.py b/notebooks/_solutions/case2_observations_processing10.py
@@ -1,4 +1,4 @@
-(survey_data_decoupled
-     .groupby("year")
-     .size()
-     .plot(kind='barh', color="#00007f", figsize=(10, 10)))
+(survey_data_decoupled["year"]
+     .value_counts(sort=False)
+     .sort_index()
+     .plot(kind='barh', color="#00007f", figsize=(10, 10)));
diff --git a/notebooks/_solutions/case2_observations_processing11.py b/notebooks/_solutions/case2_observations_processing11.py
@@ -1,4 +1,4 @@
 (survey_data_decoupled
-     .groupby(survey_data_decoupled["eventDate"].dt.year)
+     .groupby("year")
      .size()
      .plot(kind='barh', color="#00007f", figsize=(10, 10)))
diff --git a/notebooks/_solutions/case2_observations_processing12.py b/notebooks/_solutions/case2_observations_processing12.py
@@ -1,10 +1,4 @@
-nrecords_by_dayofweek = survey_data_decoupled.groupby(survey_data_decoupled["eventDate"].dt.dayofweek).size()
-
-fig, ax = plt.subplots(figsize=(6, 6))
-nrecords_by_dayofweek.plot(kind="barh", color="#00007f", ax=ax);
-# If you want to represent the ticklabels as proper names, uncomment the following line:
-# ax.set_yticklabels(["Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday"]);
-
-# Python standard library has a lot of useful functionalities! So why not use them?
-#import calendar
-#ax.set_yticklabels(calendar.day_name);
+(survey_data_decoupled
+     .groupby(survey_data_decoupled["eventDate"].dt.year)
+     .size()
+     .plot(kind='barh', color="#00007f", figsize=(10, 10)))
diff --git a/notebooks/_solutions/case2_observations_processing13.py b/notebooks/_solutions/case2_observations_processing13.py
@@ -1 +1,10 @@
-survey_data_decoupled = survey_data_decoupled.drop(columns=["day", "month", "year"])
+nrecords_by_dayofweek = survey_data_decoupled["eventDate"].dt.dayofweek.value_counts().sort_index()
+
+fig, ax = plt.subplots(figsize=(6, 6))
+nrecords_by_dayofweek.plot(kind="barh", color="#00007f", ax=ax);
+# If you want to represent the ticklabels as proper names, uncomment the following line:
+# ax.set_yticklabels(["Monday", "Tuesday", "Wednesday", "Thursday", "Friday", "Saturday", "Sunday"]);
+
+# Python standard library has a lot of useful functionalities! So why not use them?
+#import calendar
+#ax.set_yticklabels(calendar.day_name);
diff --git a/notebooks/_solutions/case2_observations_processing15.py b/notebooks/_solutions/case2_observations_processing15.py
@@ -1,15 +1,15 @@
 def transform_utm_to_wgs(row):
     """Converts the x and y coordinates
-    
+
     Parameters
     ----------
     row : pd.Series
         Single DataFrame row
-    
+
     Returns
     -------
     pd.Series with longitude and latitude
     """
     transformer = Transformer.from_crs("EPSG:32612", "epsg:4326")
-    
+
     return pd.Series(transformer.transform(row['xutm'], row['yutm']))
diff --git a/notebooks/_solutions/case2_observations_processing20.py b/notebooks/_solutions/case2_observations_processing20.py
@@ -1,2 +1,2 @@
-survey_data_plots = pd.merge(survey_data_decoupled, plot_data_selection, 
+survey_data_plots = pd.merge(survey_data_decoupled, plot_data_selection,
                              how="left", on="plot")
diff --git a/notebooks/_solutions/case2_observations_processing24.py b/notebooks/_solutions/case2_observations_processing24.py
@@ -1,17 +1,17 @@
 def name_match(genus_name, species_name, strict=True):
     """
     Perform a GBIF name matching using the species and genus names
-    
+
     Parameters
     ----------
     genus_name: str
         name of the genus of the species
     species_name: str
         name of the species to request more information
     strict: boolean
-        define if the mathing need to be performed with the strict 
+        define if the mathing need to be performed with the strict
         option (True) or not (False)
-    
+
     Returns
     -------
     message: dict
diff --git a/notebooks/_solutions/case2_observations_processing27.py b/notebooks/_solutions/case2_observations_processing27.py
@@ -1,3 +1,3 @@
-unique_species["name"] = unique_species["genus"] + " " + unique_species["species"] 
+unique_species["name"] = unique_species["genus"] + " " + unique_species["species"]
 # an alternative approach worthwhile to know:
 #unique_species["name"] = unique_species["genus"].str.cat(unique_species["species"], " ")
diff --git a/notebooks/_solutions/case2_observations_processing29.py b/notebooks/_solutions/case2_observations_processing29.py
@@ -1,2 +1,2 @@
-df_species_annotated_subset = df_species_annotated[['class', 'kingdom', 'order', 'phylum', 
+df_species_annotated_subset = df_species_annotated[['class', 'kingdom', 'order', 'phylum',
                                                     'scientificName', 'status', 'usageKey']]
diff --git a/notebooks/_solutions/case2_observations_processing30.py b/notebooks/_solutions/case2_observations_processing30.py
diff --git a/notebooks/_solutions/case2_observations_processing31.py b/notebooks/_solutions/case2_observations_processing31.py
diff --git a/notebooks/_solutions/case2_observations_processing7.py b/notebooks/_solutions/case2_observations_processing7.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment1.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment1.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment10.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment10.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment11.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment11.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment13.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment13.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment2.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment2.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment3.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment3.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment4.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment4.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment5.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment5.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment8.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment8.py
diff --git a/notebooks/_solutions/case3_bacterial_resistance_lab_experiment9.py b/notebooks/_solutions/case3_bacterial_resistance_lab_experiment9.py
diff --git a/notebooks/case1_bike_count.ipynb b/notebooks/case1_bike_count.ipynb
diff --git a/notebooks/case2_observations_analysis.ipynb b/notebooks/case2_observations_analysis.ipynb
diff --git a/notebooks/case2_observations_processing.ipynb b/notebooks/case2_observations_processing.ipynb
diff --git a/notebooks/case3_bacterial_resistance_lab_experiment.ipynb b/notebooks/case3_bacterial_resistance_lab_experiment.ipynb

Original file line number	Diff line number	Diff line change
`@@ -1,2 +1,2 @@`
`1`		`-df2 = df2.rename(columns={'ri Centrum': 'direction_centre',`
	`1`	`+df2 = df2.rename(columns={'ri Centrum': 'direction_centre',`
`2`	`2`	`'ri Mariakerke':'direction_mariakerke'})`
Original file line number	Diff line number	Diff line change
`@@ -1,2 +1,2 @@`
`1`		`-survey_data_processed = pd.read_csv("data/survey_data_completed.csv",`
	`1`	`+survey_data_processed = pd.read_csv("data/survey_data_completed.csv",`
`2`	`2`	`parse_dates=['eventDate'], index_col="occurrenceID")`
Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-survey_data.groupby("name").size().nlargest(8)`
	`1`	`+non_rodent_species = survey_data[survey_data['taxa'].isin(['Rabbit', 'Bird', 'Reptile'])]`
Original file line number	Diff line number	Diff line change
`@@ -1 +1 @@`
`1`		`-survey_data['name'].value_counts()[:8]`
	`1`	`+r_species = survey_data[survey_data['name'].str.lower().str.startswith('r')]`